LDDMM: how To Bring Deformations from Subject-Specific Atlases Into the Tangent Space at the Global Atlas#
Load meshes:
Use DenseMaternalMeshLoader to load left hippocampus structure for all three subjects
Create subject-specific pre-pregnancy atlases:
For each subject i:
Get pre-pregnancy meshes of left hippocampus
Compute subject-specific pre-pregnancy atlas \(X_{i, \text{pre-pregnancy}}\).
Create global pre-pregnancy atlas:
Compute global pre-pregnancy atlas from subject-specific pre-pregnancy atlases: \(X^{\text{pre-pregnancy}} = \text{mean}_i ~~X^{\text{pre-pregnancy}}_{i}\).
Extract pregnancy deformations as momenta:
For each subject i and pregnancy timepoint t:
Compute deformation from pre-pregnancy atlas to each pregnancy mesh, using control points of global atlas: \(\text{deformation}_{it} = X^{\text{pre-pregnancy}}_{i} \rightarrow X^{\text{pregnancy}}_{it}\) as momenta at control points
Parallel transport deformation into global deterministic atlas space to get Xit: this is assumed to be the identity
Build prediction model:
Use linear regression to predict gestational week (Yit=t) from transported deformations (Xit)
[1]:
from pathlib import Path
import numpy as np
import pyvista as pv
import polpo.lddmm as plddmm
from polpo.preprocessing import Map
from polpo.preprocessing.load.pregnancy.jacobs import TabularDataLoader, MeshLoader
from polpo.preprocessing.mesh.io import PvReader, PvWriter, DictMeshWriter
from polpo.preprocessing.mesh.registration import RigidAlignment
from polpo.preprocessing.mesh.decimation import PvDecimate
import polpo.preprocessing.dict as ppdict
import polpo.preprocessing.pd as ppd
import polpo.utils as putils
No CUDA runtime is found, using CUDA_HOME='/usr'
[2]:
STATIC_VIZ = True
if STATIC_VIZ:
pv.set_jupyter_backend("static")
[3]:
SUBJECT_IDS = ["01", "1001B", "1004B"]
RESULTS_DIR = Path("results") / "regression_example"
ATLAS_DIR = RESULTS_DIR / "atlases"
REGISTRATIONS_DIR = RESULTS_DIR / "registrations"
TRANSPORTS_DIR = RESULTS_DIR / "transports"
# SUBJECT_ATLAS_DIR = {
# "01": ATLAS_DIR / "subject01_atlas",
# "1001B": ATLAS_DIR / "subject1001_atlas",
# "1004B": ATLAS_DIR / "subject1004_atlas",
# }
# SUBJECT_REGISTRATION_DIR = {
# "01": REGISTRATIONS_DIR / "subject01_registrations",
# "1001B": REGISTRATIONS_DIR / "subject1001_registrations",
# "1004B": REGISTRATIONS_DIR / "subject1004_registrations",
# }
# TRANSPORTS_DIR.mkdir(parents=True, exist_ok=True)
# SUBJECT_TRANSPORTS_DIR = {
# "01B": TRANSPORTS_DIR / "01",
# "1001B": TRANSPORTS_DIR / "1001",
# "1004B": TRANSPORTS_DIR / "1004",
# }
RESULTS_DIR.mkdir(parents=True, exist_ok=True)
# # TODO: make it simpler
# for dir in [ATLAS_DIR, REGISTRATIONS_DIR, GLOBAL_ATLAS_DIR, TRANSPORTS_DIR]:
# dir.mkdir(parents=True, exist_ok=True)
# for subject_id in SUBJECT_IDS:
# SUBJECT_ATLAS_DIR[subject_id].mkdir(parents=True, exist_ok=True)
# SUBJECT_REGISTRATION_DIR[subject_id].mkdir(parents=True, exist_ok=True)
# SUBJECT_TRANSPORTS_DIR[subject_id].mkdir(parents=True, exist_ok=True)
[4]:
def _sub_id2name(sub_id):
return f"sub_{sub_id}"
Load meshes#
[5]:
path2meshes = MeshLoader(
subject_subset=SUBJECT_IDS, struct_subset=["L_Hipp"], as_mesh=True
) + ppdict.ExtractUniqueKey(nested=True)
# subject_id, session_id
raw_meshes = path2meshes()
print("Number of meshes for:")
for subject_id, meshes in raw_meshes.items():
print(f" -subject {subject_id}: {len(meshes)}")
Number of meshes for:
-subject 01: 27
-subject 1001B: 13
-subject 1004B: 21
[6]:
csvs = {
subject_id: TabularDataLoader(subject_id=subject_id)() for subject_id in SUBJECT_IDS
}
for subject_id in SUBJECT_IDS:
display(csvs[subject_id])
INFO: Data has already been downloaded... using cached file ('/home/luisfpereira/.herbrain/data/maternal/maternal_brain_project_pilot/rawdata/28Baby_Hormones.csv').
| estro | prog | lh | gestWeek | stage | EndoStatus | trimester | |
|---|---|---|---|---|---|---|---|
| sessionID | |||||||
| 1 | NaN | NaN | NaN | -3.0 | pre | pilot1 | pre |
| 2 | 3.42 | 0.840 | NaN | -0.5 | pre | pilot2 | pre |
| 3 | 386.00 | NaN | NaN | 1.0 | pre | IVF | pre |
| 4 | 1238.00 | NaN | NaN | 1.5 | pre | IVF | pre |
| 5 | 1350.00 | 2.940 | NaN | 2.0 | pre | IVF | first |
| 6 | 241.00 | 8.760 | NaN | 3.0 | preg | Pregnant | first |
| 7 | NaN | NaN | NaN | 9.0 | preg | Pregnant | first |
| 8 | NaN | NaN | NaN | 12.0 | preg | Pregnant | first |
| 9 | NaN | NaN | NaN | 14.0 | preg | Pregnant | second |
| 10 | 4700.00 | 53.900 | 1.45 | 15.0 | preg | Pregnant | second |
| 11 | 4100.00 | 56.800 | 0.87 | 17.0 | preg | Pregnant | second |
| 12 | 6190.00 | 70.600 | 0.93 | 19.0 | preg | Pregnant | second |
| 13 | 9640.00 | 54.700 | 0.62 | 22.0 | preg | Pregnant | second |
| 14 | 8800.00 | 64.100 | 0.73 | 24.0 | preg | Pregnant | second |
| 15 | 8970.00 | 61.400 | 0.73 | 27.0 | preg | Pregnant | third |
| 16 | 10200.00 | 74.200 | 0.69 | 29.0 | preg | Pregnant | third |
| 17 | 9920.00 | 83.000 | 0.77 | 31.0 | preg | Pregnant | third |
| 18 | 9860.00 | 95.300 | 0.83 | 33.0 | preg | Pregnant | third |
| 19 | 12400.00 | 103.000 | 0.59 | 36.0 | preg | Pregnant | third |
| 20 | 9.18 | 0.120 | 0.96 | 43.0 | post | Postpartum | post |
| 21 | 20.70 | 0.043 | 4.01 | 46.0 | post | Postpartum | post |
| 22 | 17.50 | 0.068 | 7.58 | 49.0 | post | Postpartum | post |
| 23 | 11.50 | 0.042 | 4.67 | 51.0 | post | Postpartum | post |
| 24 | NaN | NaN | NaN | 68.0 | post | Postpartum | post |
| 25 | NaN | NaN | NaN | 93.0 | post | Postpartum | post |
| 26 | NaN | NaN | NaN | 162.0 | post | Postpartum | post |
| 27 | NaN | NaN | NaN | 162.0 | post | Postpartum | post |
| gestWeek | stage | trimester | date | |
|---|---|---|---|---|
| sessionID | ||||
| base1 | -18.0 | pre | pre | 4/1/2023 |
| base2 | -13.0 | pre | pre | 5/6/2023 |
| gest1 | 8.0 | preg | first | 9/30/2023 |
| gest2 | 13.0 | preg | first | 11/4/2023 |
| gest3 | 17.0 | preg | second | 12/2/2023 |
| gest4 | 22.0 | preg | second | 1/6/2024 |
| gest5 | 26.0 | preg | second | 2/3/2024 |
| gest6 | 30.0 | preg | third | 3/2/2024 |
| gest7 | 35.0 | preg | third | 4/6/2024 |
| post1 | 43.0 | post | post | 6/1/2024 |
| post2 | 48.0 | post | post | 7/6/2024 |
| post3 | 56.0 | post | post | 9/1/2024 |
| post4 | 65.0 | post | post | 11/2/2024 |
| gestWeek | stage | trimester | date | |
|---|---|---|---|---|
| sessionID | ||||
| base1 | -2.5 | pre | pre | 8/22/2023 |
| base2 | 2.0 | preg | first | 9/21/2023 |
| gest1 | 5.0 | preg | first | 10/11/2023 |
| gest2 | 7.0 | preg | first | 10/26/2023 |
| gest3 | 8.5 | preg | first | 11/7/2023 |
| gest4 | 10.5 | preg | first | 11/20/2023 |
| gest5 | 12.5 | preg | first | 12/4/2023 |
| gest6 | 14.5 | preg | second | 12/18/2023 |
| gest7 | 16.5 | preg | second | 1/3/2024 |
| gest8 | 19.0 | preg | second | 1/18/2024 |
| gest9 | 21.0 | preg | second | 2/1/2024 |
| gest10 | 23.0 | preg | second | 2/15/2024 |
| gest11 | 24.5 | preg | second | 2/27/2024 |
| gest12 | 27.0 | preg | third | 3/14/2024 |
| gest13 | 30.0 | preg | third | 4/5/2024 |
| post1 | 43.0 | post | post | 7/5/2024 |
| post2 | 50.0 | post | post | 8/21/2024 |
| post3 | 52.0 | post | post | 9/4/2024 |
| post4 | 54.0 | post | post | 9/23/2024 |
| post5 | 57.0 | post | post | 10/10/2024 |
| post6 | 65.5 | post | post | 12/11/2024 |
[7]:
# Rigid alignment of all meshes to the first mesh of subject 01
align_pipe = RigidAlignment(
target=putils.get_first(raw_meshes["01"]),
# TODO: update here
max_iterations=10,
)
# Coarsen all meshes to reduce number of vertices
decimate_pipe = PvDecimate(target_reduction=0.6)
# TODO: it is better to go the other way around
rigidly_aligned_meshes = ppdict.DictMap(align_pipe)(raw_meshes)
meshes = ppdict.NestedDictMap(decimate_pipe)(rigidly_aligned_meshes)
[8]:
pl = pv.Plotter(shape=(2, 3), border=False, window_size=[600, 300])
for i, subject_id in enumerate(SUBJECT_IDS):
pl.subplot(0, i)
pl.add_mesh(putils.get_first(rigidly_aligned_meshes[subject_id]), show_edges=True)
pl.add_text(
f"First mesh of subject {subject_id}", position="upper_edge", font_size=4
)
pl.subplot(1, i)
pl.add_mesh(putils.get_first(meshes[subject_id]), show_edges=True, color="white")
pl.add_text(
f"Decimated First Mesh of subject {subject_id}",
position="upper_edge",
font_size=4,
)
pl.show()
Estimate deterministic atlas for subject and global#
Compute subject specific deterministic atlas by averaging pre-pregnancy meshes.
First, we select the pre-pregnancy meshes.
[9]:
pre_keys_selector = ppd.DfIsInFilter("stage", ["pre"]) + (lambda x: x.index)
pre_keys = ppdict.DictMap(pre_keys_selector)(csvs)
pre_meshes = {
subject_id: ppdict.SelectKeySubset(pre_keys[subject_id])(meshes)
for subject_id, meshes in meshes.items()
}
[10]:
pre_meshes
[10]:
{'01': {1: PolyData (0x777b6a212ce0)
N Cells: 584
N Points: 294
N Strips: 0
X Bounds: 9.432e+01, 1.175e+02
Y Bounds: 7.762e+01, 1.171e+02
Z Bounds: 1.080e+02, 1.255e+02
N Arrays: 0,
2: PolyData (0x777b6a2117e0)
N Cells: 584
N Points: 294
N Strips: 0
X Bounds: 9.416e+01, 1.172e+02
Y Bounds: 7.753e+01, 1.170e+02
Z Bounds: 1.080e+02, 1.256e+02
N Arrays: 0,
3: PolyData (0x777b6a212c80)
N Cells: 584
N Points: 294
N Strips: 0
X Bounds: 9.450e+01, 1.172e+02
Y Bounds: 7.723e+01, 1.172e+02
Z Bounds: 1.082e+02, 1.257e+02
N Arrays: 0,
4: PolyData (0x777b6a212d40)
N Cells: 584
N Points: 294
N Strips: 0
X Bounds: 9.465e+01, 1.173e+02
Y Bounds: 7.734e+01, 1.171e+02
Z Bounds: 1.077e+02, 1.259e+02
N Arrays: 0,
5: PolyData (0x777b6a212da0)
N Cells: 584
N Points: 294
N Strips: 0
X Bounds: 9.463e+01, 1.172e+02
Y Bounds: 7.744e+01, 1.170e+02
Z Bounds: 1.080e+02, 1.257e+02
N Arrays: 0},
'1001B': {'base1': PolyData (0x777b6a213640)
N Cells: 584
N Points: 294
N Strips: 0
X Bounds: 9.305e+01, 1.173e+02
Y Bounds: 7.844e+01, 1.163e+02
Z Bounds: 1.082e+02, 1.248e+02
N Arrays: 0,
'base2': PolyData (0x777b6a2136a0)
N Cells: 584
N Points: 294
N Strips: 0
X Bounds: 9.298e+01, 1.180e+02
Y Bounds: 7.853e+01, 1.167e+02
Z Bounds: 1.083e+02, 1.251e+02
N Arrays: 0},
'1004B': {'base1': PolyData (0x777b6a213b20)
N Cells: 584
N Points: 294
N Strips: 0
X Bounds: 9.585e+01, 1.148e+02
Y Bounds: 7.547e+01, 1.177e+02
Z Bounds: 1.072e+02, 1.259e+02
N Arrays: 0}}
[11]:
def _key2name(key):
sub_id, session_id = key.split("/")
return f"{_sub_id2name(sub_id)}/mesh_{session_id}"
meshes2files = (
ppdict.UnnestDict(sep="/")
+ DictMeshWriter(dirname=REGISTRATIONS_DIR, ext="vtk", key2name=_key2name)
+ ppdict.NestDict(sep="/")
)
# subject, session, filename
dataset = meshes2files(pre_meshes)
Closely follows LDDMM: how to estimate a deterministic atlas?.
[12]:
kernel_width = 10.0 # NB: influences the number of cp
registration_kwargs = dict(
kernel_width=kernel_width,
regularisation=1,
max_iter=2000,
freeze_control_points=False,
metric="varifold",
attachment_kernel_width=2.0,
tol=1e-10,
)
[14]:
templates = {}
for subject_id, dataset_ in dataset.items():
template = plddmm.estimate_deterministic_atlas(
source=putils.get_first(dataset_),
targets=dataset_,
output_dir=ATLAS_DIR / _sub_id2name(subject_id),
initial_step_size=1e-1,
**registration_kwargs,
)
templates[subject_id] = template
templates["global"] = plddmm.estimate_deterministic_atlas(
source=putils.get_first(templates),
targets=templates,
output_dir=ATLAS_DIR / "global",
initial_step_size=1e-1,
**registration_kwargs,
)
templates = ppdict.DictMap(PvReader())(templates)
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10.0
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 10
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/regression_example/atlases/sub_01/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
{'max_iterations': 2000, 'freeze_template': False, 'freeze_control_points': False, 'freeze_momenta': False, 'use_sobolev_gradient': True, 'sobolev_kernel_width_ratio': 1, 'max_line_search_iterations': 50, 'initial_control_points': None, 'initial_cp_spacing': None, 'initial_momenta': None, 'dense_mode': False, 'number_of_threads': 1, 'print_every_n_iters': 20, 'downsampling_factor': 1, 'dimension': 3, 'optimization_method_type': 'ScipyLBFGS', 'convergence_tolerance': 1e-10, 'initial_step_size': 0.1, 'gpu_mode': <GpuMode.KERNEL: 4>, 'state_file': 'results/regression_example/atlases/sub_01/deformetrica-state.p', 'load_state_file': False, 'memory_length': 10}
instantiating kernel torch with kernel_width 10.0 and gpu_mode GpuMode.KERNEL. addr: 0x777b6a21b090
instantiating kernel torch with kernel_width 2.0 and gpu_mode GpuMode.KERNEL. addr: 0x777b63f077d0
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 5 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.255E+03 [ attachment = -3.249E+03 ; regularity = -6.260E+00 ]
>> Gradient at Termination: 64726.30970460872
>> CONVERGENCE: REL_REDUCTION_OF_F_<=_FACTR*EPSMCH
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10.0
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 10
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/regression_example/atlases/sub_1001B/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
{'max_iterations': 2000, 'freeze_template': False, 'freeze_control_points': False, 'freeze_momenta': False, 'use_sobolev_gradient': True, 'sobolev_kernel_width_ratio': 1, 'max_line_search_iterations': 50, 'initial_control_points': None, 'initial_cp_spacing': None, 'initial_momenta': None, 'dense_mode': False, 'number_of_threads': 1, 'print_every_n_iters': 20, 'downsampling_factor': 1, 'dimension': 3, 'optimization_method_type': 'ScipyLBFGS', 'convergence_tolerance': 1e-10, 'initial_step_size': 0.1, 'gpu_mode': <GpuMode.KERNEL: 4>, 'state_file': 'results/regression_example/atlases/sub_1001B/deformetrica-state.p', 'load_state_file': False, 'memory_length': 10}
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 2 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Gradient at Termination: 40015.72149555154
>> CONVERGENCE: REL_REDUCTION_OF_F_<=_FACTR*EPSMCH
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10.0
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 10
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/regression_example/atlases/sub_1004B/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
{'max_iterations': 2000, 'freeze_template': False, 'freeze_control_points': False, 'freeze_momenta': False, 'use_sobolev_gradient': True, 'sobolev_kernel_width_ratio': 1, 'max_line_search_iterations': 50, 'initial_control_points': None, 'initial_cp_spacing': None, 'initial_momenta': None, 'dense_mode': False, 'number_of_threads': 1, 'print_every_n_iters': 20, 'downsampling_factor': 1, 'dimension': 3, 'optimization_method_type': 'ScipyLBFGS', 'convergence_tolerance': 1e-10, 'initial_step_size': 0.1, 'gpu_mode': <GpuMode.KERNEL: 4>, 'state_file': 'results/regression_example/atlases/sub_1004B/deformetrica-state.p', 'load_state_file': False, 'memory_length': 10}
>> Set of 20 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
>> Gradient at Termination: 44972.02116515963
>> CONVERGENCE: REL_REDUCTION_OF_F_<=_FACTR*EPSMCH
>> Estimation took: 00 seconds
Deformetrica.__del__()
[20]:
pl = pv.Plotter(shape=(1, 4), border=False, window_size=[800, 150])
for i, subject_id in enumerate(SUBJECT_IDS):
pl.subplot(0, i)
pl.add_mesh(templates[subject_id], show_edges=True)
pl.add_text(
f"pre-pregnancy template of {subject_id}", position="upper_edge", font_size=4
)
pl.subplot(0, 3)
pl.add_mesh(templates["global"], show_edges=True)
pl.add_text("global template", position="upper_edge", font_size=4)
pl.show()
[ ]:
[ ]:
# parallel transport the momenta (?) of each subject from its subject-specific template to the global template
n_rungs = 11
transport_args = {"kernel_type": "torch", "kernel_width": 4, "n_rungs": 11}
shoot_args = {
"use_rk2_for_flow": True,
"kernel_width": registration_kwargs["kernel_width"],
"number_of_time_steps": n_rungs + 1,
"write_params": False,
}
# NOTE : according to deformetrica, the main geodesic needs to be estimated with rk4
fixed_control_points_registration_kwargs = {
**registration_kwargs,
"freeze_control_points": True,
# get the control points of the global atlas (mapping to each subject-specific pre-pregnancy atlasees)
"initial_control_points": GLOBAL_ATLAS_DIR / lddmm_strings.cp_str,
"use_rk4_for_flow": True,
"use_rk4_for_shoot": True,
}
control_points = {
"01": {},
"1001": {},
"1004": {},
}
momenta = {
"01": {},
"1001": {},
"1004": {},
}
# WARNING: This takes 10minutes
for subject_id in SUBJECT_IDS:
mesh_writer = Map(PvWriter(dirname=SUBJECT_TRANSPORTS_DIR[subject_id], ext="vtk"))
for i_mesh, mesh in enumerate(meshes[subject_id]):
print(f"transporting mesh {i_mesh} of subject {subject_id}")
cp, mom = lddmm.geometry.parallel_transport_from_meshes(
source=SUBJECT_ATLAS_DIR[subject_id] / lddmm_strings.template_str,
target=mesh_writer([(f"mesh_{i_mesh}", mesh)])[0],
atlas=GLOBAL_ATLAS_DIR / lddmm_strings.template_str,
name=f"transport_{subject_id}_mesh_{i_mesh}",
output_dir=SUBJECT_TRANSPORTS_DIR[subject_id]
/ f"transported_mesh_{i_mesh}",
registration_args=registration_kwargs,
transport_args=transport_args,
main_reg_dir=None,
)
control_points[subject_id][i_mesh] = cp
momenta[subject_id][i_mesh] = mom
transporting mesh 0 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_0/transport_01_mesh_0/time_reg_transport_01_mesh_0/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.903E+00 [ attachment = -3.312E+00 ; regularity = -5.908E-01 ]
>> Gradient at Termination: 186.50340284275254
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_0/transport_01_mesh_0/main_reg_transport_01_mesh_0/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 1 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_1/transport_01_mesh_1/time_reg_transport_01_mesh_1/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -1.597E+01 [ attachment = -1.456E+01 ; regularity = -1.405E+00 ]
>> Gradient at Termination: 88.28497387153153
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_1/transport_01_mesh_1/main_reg_transport_01_mesh_1/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 2 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_2/transport_01_mesh_2/time_reg_transport_01_mesh_2/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.250E+01 [ attachment = -2.081E+01 ; regularity = -1.691E+00 ]
>> Gradient at Termination: 230.71896453007517
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_2/transport_01_mesh_2/main_reg_transport_01_mesh_2/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 3 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_3/transport_01_mesh_3/time_reg_transport_01_mesh_3/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.140E+01 [ attachment = -1.962E+01 ; regularity = -1.777E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.561E+01 [ attachment = -1.231E+01 ; regularity = -3.295E+00 ]
>> Log-likelihood = -1.562E+01 [ attachment = -1.231E+01 ; regularity = -3.312E+00 ]
>> Log-likelihood = -1.544E+01 [ attachment = -1.212E+01 ; regularity = -3.314E+00 ]
>> Log-likelihood = -1.525E+01 [ attachment = -1.194E+01 ; regularity = -3.314E+00 ]
>> Log-likelihood = -1.525E+01 [ attachment = -1.194E+01 ; regularity = -3.314E+00 ]
>> Log-likelihood = -1.525E+01 [ attachment = -1.194E+01 ; regularity = -3.314E+00 ]
>> Log-likelihood = -1.556E+01 [ attachment = -1.225E+01 ; regularity = -3.314E+00 ]
>> Log-likelihood = -1.525E+01 [ attachment = -1.194E+01 ; regularity = -3.314E+00 ]
>> Log-likelihood = -1.544E+01 [ attachment = -1.212E+01 ; regularity = -3.314E+00 ]
>> Log-likelihood = -1.525E+01 [ attachment = -1.194E+01 ; regularity = -3.314E+00 ]
>> Log-likelihood = -3.721E+05 [ attachment = -3.716E+05 ; regularity = -4.794E+02 ]
>> Log-likelihood = -1.531E+01 [ attachment = -1.200E+01 ; regularity = -3.314E+00 ]
>> Gradient at Termination: 129.67331998438837
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_3/transport_01_mesh_3/main_reg_transport_01_mesh_3/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 4 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_4/transport_01_mesh_4/time_reg_transport_01_mesh_4/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.665E+01 [ attachment = -2.412E+01 ; regularity = -2.524E+00 ]
>> Gradient at Termination: 1812.8686561117825
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_4/transport_01_mesh_4/main_reg_transport_01_mesh_4/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 5 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_5/transport_01_mesh_5/time_reg_transport_01_mesh_5/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -6.587E+01 [ attachment = -5.906E+01 ; regularity = -6.803E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -4.678E+01 [ attachment = -3.488E+01 ; regularity = -1.190E+01 ]
>> Gradient at Termination: 169.4251386712636
>> CONVERGENCE: RELATIVE REDUCTION OF F <= FACTR*EPSMCH
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_5/transport_01_mesh_5/main_reg_transport_01_mesh_5/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 6 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_6/transport_01_mesh_6/time_reg_transport_01_mesh_6/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -6.572E+01 [ attachment = -5.781E+01 ; regularity = -7.909E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -4.583E+01 [ attachment = -3.244E+01 ; regularity = -1.340E+01 ]
>> Log-likelihood = -4.387E+01 [ attachment = -3.088E+01 ; regularity = -1.300E+01 ]
>> Gradient at Termination: 390.0208455515726
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_6/transport_01_mesh_6/main_reg_transport_01_mesh_6/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 7 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_7/transport_01_mesh_7/time_reg_transport_01_mesh_7/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.735E+01 [ attachment = -2.438E+01 ; regularity = -2.973E+00 ]
>> Gradient at Termination: 350.349873717455
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_7/transport_01_mesh_7/main_reg_transport_01_mesh_7/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 8 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_8/transport_01_mesh_8/time_reg_transport_01_mesh_8/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.009E+01 [ attachment = -1.831E+01 ; regularity = -1.776E+00 ]
>> Gradient at Termination: 1835.4374961497535
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_8/transport_01_mesh_8/main_reg_transport_01_mesh_8/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 9 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_9/transport_01_mesh_9/time_reg_transport_01_mesh_9/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.169E+01 [ attachment = -2.750E+01 ; regularity = -4.186E+00 ]
>> Gradient at Termination: 265.22631604203514
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_9/transport_01_mesh_9/main_reg_transport_01_mesh_9/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 10 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_10/transport_01_mesh_10/time_reg_transport_01_mesh_10/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.485E+01 [ attachment = -3.200E+01 ; regularity = -2.853E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.617E+01 [ attachment = -2.094E+01 ; regularity = -5.232E+00 ]
>> Log-likelihood = -2.596E+01 [ attachment = -2.088E+01 ; regularity = -5.088E+00 ]
>> Log-likelihood = -2.607E+01 [ attachment = -2.100E+01 ; regularity = -5.069E+00 ]
>> Log-likelihood = -2.601E+01 [ attachment = -2.094E+01 ; regularity = -5.068E+00 ]
>> Log-likelihood = -2.588E+01 [ attachment = -2.081E+01 ; regularity = -5.068E+00 ]
>> Log-likelihood = -2.588E+01 [ attachment = -2.081E+01 ; regularity = -5.068E+00 ]
>> Log-likelihood = -2.588E+01 [ attachment = -2.081E+01 ; regularity = -5.068E+00 ]
>> Log-likelihood = -2.588E+01 [ attachment = -2.081E+01 ; regularity = -5.068E+00 ]
>> Log-likelihood = -2.588E+01 [ attachment = -2.081E+01 ; regularity = -5.068E+00 ]
>> Log-likelihood = -2.588E+01 [ attachment = -2.081E+01 ; regularity = -5.068E+00 ]
>> Log-likelihood = -9.287E+05 [ attachment = -9.276E+05 ; regularity = -1.115E+03 ]
>> Log-likelihood = -2.600E+01 [ attachment = -2.094E+01 ; regularity = -5.067E+00 ]
>> Log-likelihood = -2.582E+01 [ attachment = -2.075E+01 ; regularity = -5.068E+00 ]
>> Log-likelihood = -2.594E+01 [ attachment = -2.088E+01 ; regularity = -5.068E+00 ]
>> Log-likelihood = -2.582E+01 [ attachment = -2.075E+01 ; regularity = -5.068E+00 ]
>> Gradient at Termination: 474.9616828657407
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_10/transport_01_mesh_10/main_reg_transport_01_mesh_10/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 11 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_11/transport_01_mesh_11/time_reg_transport_01_mesh_11/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.104E+01 [ attachment = -2.756E+01 ; regularity = -3.476E+00 ]
>> Log-likelihood = -2.974E+01 [ attachment = -2.644E+01 ; regularity = -3.298E+00 ]
>> Gradient at Termination: 1035.5200357657009
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_11/transport_01_mesh_11/main_reg_transport_01_mesh_11/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 12 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_12/transport_01_mesh_12/time_reg_transport_01_mesh_12/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -5.796E+01 [ attachment = -5.212E+01 ; regularity = -5.836E+00 ]
>> Gradient at Termination: 2493.9658676687145
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_12/transport_01_mesh_12/main_reg_transport_01_mesh_12/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 13 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_13/transport_01_mesh_13/time_reg_transport_01_mesh_13/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.535E+01 [ attachment = -3.206E+01 ; regularity = -3.284E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.565E+01 [ attachment = -2.038E+01 ; regularity = -5.270E+00 ]
>> Gradient at Termination: 67.24440542846878
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_13/transport_01_mesh_13/main_reg_transport_01_mesh_13/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 14 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_14/transport_01_mesh_14/time_reg_transport_01_mesh_14/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.441E+01 [ attachment = -2.919E+01 ; regularity = -5.223E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.584E+01 [ attachment = -1.906E+01 ; regularity = -6.779E+00 ]
>> Gradient at Termination: 152.9842147547948
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_14/transport_01_mesh_14/main_reg_transport_01_mesh_14/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 15 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_15/transport_01_mesh_15/time_reg_transport_01_mesh_15/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.380E+01 [ attachment = -2.144E+01 ; regularity = -2.363E+00 ]
>> Gradient at Termination: 783.2804665218616
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_15/transport_01_mesh_15/main_reg_transport_01_mesh_15/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 16 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_16/transport_01_mesh_16/time_reg_transport_01_mesh_16/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.258E+01 [ attachment = -2.106E+01 ; regularity = -1.516E+00 ]
>> Gradient at Termination: 220.49477585756216
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_16/transport_01_mesh_16/main_reg_transport_01_mesh_16/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 17 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_17/transport_01_mesh_17/time_reg_transport_01_mesh_17/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.036E+01 [ attachment = -1.856E+01 ; regularity = -1.793E+00 ]
>> Gradient at Termination: 534.4855690164555
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_17/transport_01_mesh_17/main_reg_transport_01_mesh_17/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 18 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_18/transport_01_mesh_18/time_reg_transport_01_mesh_18/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -1.532E+01 [ attachment = -1.362E+01 ; regularity = -1.690E+00 ]
>> Log-likelihood = -1.513E+01 [ attachment = -1.350E+01 ; regularity = -1.632E+00 ]
>> Gradient at Termination: 937.592091333186
>> ABNORMAL:
>> Estimation took: 01 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_18/transport_01_mesh_18/main_reg_transport_01_mesh_18/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 19 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_19/transport_01_mesh_19/time_reg_transport_01_mesh_19/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.388E+01 [ attachment = -2.212E+01 ; regularity = -1.755E+00 ]
>> Gradient at Termination: 400.51755099027633
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_19/transport_01_mesh_19/main_reg_transport_01_mesh_19/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 20 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_20/transport_01_mesh_20/time_reg_transport_01_mesh_20/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.704E+01 [ attachment = -3.444E+01 ; regularity = -2.599E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.644E+01 [ attachment = -2.125E+01 ; regularity = -5.187E+00 ]
>> Log-likelihood = -2.650E+01 [ attachment = -2.131E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.656E+01 [ attachment = -2.138E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.631E+01 [ attachment = -2.112E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -4.231E+05 [ attachment = -4.223E+05 ; regularity = -8.114E+02 ]
>> Log-likelihood = -2.638E+01 [ attachment = -2.119E+01 ; regularity = -5.189E+00 ]
>> Log-likelihood = -2.656E+01 [ attachment = -2.138E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.644E+01 [ attachment = -2.125E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Log-likelihood = -2.625E+01 [ attachment = -2.106E+01 ; regularity = -5.188E+00 ]
>> Gradient at Termination: 421.5292708851359
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_20/transport_01_mesh_20/main_reg_transport_01_mesh_20/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 21 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_21/transport_01_mesh_21/time_reg_transport_01_mesh_21/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.900E+01 [ attachment = -2.606E+01 ; regularity = -2.934E+00 ]
>> Gradient at Termination: 420.93589802234584
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_21/transport_01_mesh_21/main_reg_transport_01_mesh_21/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 22 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_22/transport_01_mesh_22/time_reg_transport_01_mesh_22/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -1.027E+02 [ attachment = -8.569E+01 ; regularity = -1.703E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -7.044E+01 [ attachment = -4.812E+01 ; regularity = -2.232E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -6.093E+01 [ attachment = -3.688E+01 ; regularity = -2.406E+01 ]
>> Gradient at Termination: 753.7132709836845
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_22/transport_01_mesh_22/main_reg_transport_01_mesh_22/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 23 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_23/transport_01_mesh_23/time_reg_transport_01_mesh_23/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.694E+01 [ attachment = -2.456E+01 ; regularity = -2.373E+00 ]
>> Gradient at Termination: 383.6066925601395
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_23/transport_01_mesh_23/main_reg_transport_01_mesh_23/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 24 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_24/transport_01_mesh_24/time_reg_transport_01_mesh_24/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.199E+01 [ attachment = -2.000E+01 ; regularity = -1.987E+00 ]
>> Gradient at Termination: 391.96281686184403
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_24/transport_01_mesh_24/main_reg_transport_01_mesh_24/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 25 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_25/transport_01_mesh_25/time_reg_transport_01_mesh_25/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -4.808E+01 [ attachment = -4.362E+01 ; regularity = -4.458E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -3.087E+01 [ attachment = -2.194E+01 ; regularity = -8.930E+00 ]
>> Log-likelihood = -3.070E+01 [ attachment = -2.188E+01 ; regularity = -8.827E+00 ]
>> Log-likelihood = -3.076E+01 [ attachment = -2.194E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -4.100E+05 [ attachment = -4.092E+05 ; regularity = -8.188E+02 ]
>> Log-likelihood = -3.082E+01 [ attachment = -2.200E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.088E+01 [ attachment = -2.206E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.069E+01 [ attachment = -2.188E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Log-likelihood = -3.044E+01 [ attachment = -2.162E+01 ; regularity = -8.818E+00 ]
>> Gradient at Termination: 424.48985721266587
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_25/transport_01_mesh_25/main_reg_transport_01_mesh_25/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 26 of subject 01
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_26/transport_01_mesh_26/time_reg_transport_01_mesh_26/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.664E+01 [ attachment = -3.394E+01 ; regularity = -2.705E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -3.020E+01 [ attachment = -2.588E+01 ; regularity = -4.329E+00 ]
>> Log-likelihood = -3.040E+01 [ attachment = -2.612E+01 ; regularity = -4.275E+00 ]
>> Log-likelihood = -3.032E+01 [ attachment = -2.606E+01 ; regularity = -4.261E+00 ]
>> Log-likelihood = -3.026E+01 [ attachment = -2.600E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.014E+01 [ attachment = -2.588E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.014E+01 [ attachment = -2.588E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.014E+01 [ attachment = -2.588E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.014E+01 [ attachment = -2.588E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.014E+01 [ attachment = -2.588E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.014E+01 [ attachment = -2.588E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.675E+05 [ attachment = -3.669E+05 ; regularity = -5.398E+02 ]
>> Log-likelihood = -3.038E+01 [ attachment = -2.612E+01 ; regularity = -4.258E+00 ]
>> Log-likelihood = -3.014E+01 [ attachment = -2.588E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.026E+01 [ attachment = -2.600E+01 ; regularity = -4.259E+00 ]
>> Log-likelihood = -3.032E+01 [ attachment = -2.606E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.014E+01 [ attachment = -2.588E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.038E+01 [ attachment = -2.612E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.007E+01 [ attachment = -2.581E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.007E+01 [ attachment = -2.581E+01 ; regularity = -4.260E+00 ]
>> Log-likelihood = -3.032E+01 [ attachment = -2.606E+01 ; regularity = -4.260E+00 ]
>> Gradient at Termination: 280.5502878607222
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/01/transported_mesh_26/transport_01_mesh_26/main_reg_transport_01_mesh_26/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.312E+02 [ attachment = -3.027E+02 ; regularity = -2.852E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.480E+02 [ attachment = -2.052E+02 ; regularity = -4.277E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -2.230E+02 [ attachment = -1.716E+02 ; regularity = -5.137E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -2.072E+02 [ attachment = -1.515E+02 ; regularity = -5.572E+01 ]
>> Log-likelihood = -2.073E+02 [ attachment = -1.515E+02 ; regularity = -5.575E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.518E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.075E+02 [ attachment = -1.517E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -2.072E+02 [ attachment = -1.514E+02 ; regularity = -5.577E+01 ]
>> Log-likelihood = -7.101E+05 [ attachment = -7.088E+05 ; regularity = -1.371E+03 ]
>> Log-likelihood = -2.069E+02 [ attachment = -1.512E+02 ; regularity = -5.576E+01 ]
>> Gradient at Termination: 1129.3542085016377
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 0 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_0/transport_1001_mesh_0/time_reg_transport_1001_mesh_0/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -1.499E+01 [ attachment = -1.362E+01 ; regularity = -1.364E+00 ]
>> Gradient at Termination: 91.08639859194206
>> CONVERGENCE: RELATIVE REDUCTION OF F <= FACTR*EPSMCH
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_0/transport_1001_mesh_0/main_reg_transport_1001_mesh_0/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 1 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_1/transport_1001_mesh_1/time_reg_transport_1001_mesh_1/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.154E+01 [ attachment = -2.912E+01 ; regularity = -2.410E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.267E+01 [ attachment = -1.812E+01 ; regularity = -4.540E+00 ]
>> Log-likelihood = -2.225E+01 [ attachment = -1.800E+01 ; regularity = -4.253E+00 ]
>> Gradient at Termination: 286.8958915399929
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_1/transport_1001_mesh_1/main_reg_transport_1001_mesh_1/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 2 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_2/transport_1001_mesh_2/time_reg_transport_1001_mesh_2/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.696E+01 [ attachment = -3.356E+01 ; regularity = -3.399E+00 ]
>> Gradient at Termination: 558.8462332248215
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_2/transport_1001_mesh_2/main_reg_transport_1001_mesh_2/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 3 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_3/transport_1001_mesh_3/time_reg_transport_1001_mesh_3/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -5.031E+01 [ attachment = -4.619E+01 ; regularity = -4.123E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -3.414E+01 [ attachment = -2.569E+01 ; regularity = -8.450E+00 ]
>> Log-likelihood = -3.394E+01 [ attachment = -2.556E+01 ; regularity = -8.377E+00 ]
>> Gradient at Termination: 233.2882951620369
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_3/transport_1001_mesh_3/main_reg_transport_1001_mesh_3/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 4 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_4/transport_1001_mesh_4/time_reg_transport_1001_mesh_4/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -4.764E+01 [ attachment = -4.488E+01 ; regularity = -2.767E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Gradient at Termination: 322.5888311540588
>> CONVERGENCE: RELATIVE REDUCTION OF F <= FACTR*EPSMCH
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_4/transport_1001_mesh_4/main_reg_transport_1001_mesh_4/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 5 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_5/transport_1001_mesh_5/time_reg_transport_1001_mesh_5/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -4.738E+01 [ attachment = -4.094E+01 ; regularity = -6.446E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -3.432E+01 [ attachment = -2.519E+01 ; regularity = -9.134E+00 ]
>> Gradient at Termination: 257.7120218883954
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_5/transport_1001_mesh_5/main_reg_transport_1001_mesh_5/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 6 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_6/transport_1001_mesh_6/time_reg_transport_1001_mesh_6/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -5.811E+01 [ attachment = -5.250E+01 ; regularity = -5.606E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -4.023E+01 [ attachment = -3.025E+01 ; regularity = -9.980E+00 ]
>> Gradient at Termination: 682.318760494234
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_6/transport_1001_mesh_6/main_reg_transport_1001_mesh_6/deformetrica-state.p.
>> Removing the pre-existing state file with same path.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 7 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_7/transport_1001_mesh_7/time_reg_transport_1001_mesh_7/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -8.117E+01 [ attachment = -7.325E+01 ; regularity = -7.919E+00 ]
>> Gradient at Termination: 824.6581408604242
>> ABNORMAL:
>> Estimation took: 01 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_7/transport_1001_mesh_7/main_reg_transport_1001_mesh_7/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 8 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_8/transport_1001_mesh_8/time_reg_transport_1001_mesh_8/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -5.154E+01 [ attachment = -4.625E+01 ; regularity = -5.286E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -3.528E+01 [ attachment = -2.656E+01 ; regularity = -8.720E+00 ]
>> Gradient at Termination: 180.98693285740654
>> CONVERGENCE: RELATIVE REDUCTION OF F <= FACTR*EPSMCH
>> Estimation took: 01 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_8/transport_1001_mesh_8/main_reg_transport_1001_mesh_8/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 9 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_9/transport_1001_mesh_9/time_reg_transport_1001_mesh_9/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -6.986E+01 [ attachment = -6.275E+01 ; regularity = -7.113E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -4.909E+01 [ attachment = -3.775E+01 ; regularity = -1.134E+01 ]
>> Gradient at Termination: 854.1550806307893
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_9/transport_1001_mesh_9/main_reg_transport_1001_mesh_9/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 10 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_10/transport_1001_mesh_10/time_reg_transport_1001_mesh_10/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -4.109E+01 [ attachment = -3.625E+01 ; regularity = -4.835E+00 ]
>> Log-likelihood = -4.078E+01 [ attachment = -3.606E+01 ; regularity = -4.719E+00 ]
>> Gradient at Termination: 770.9262312418844
>> ABNORMAL:
>> Estimation took: 01 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_10/transport_1001_mesh_10/main_reg_transport_1001_mesh_10/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 11 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_11/transport_1001_mesh_11/time_reg_transport_1001_mesh_11/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -4.778E+01 [ attachment = -4.238E+01 ; regularity = -5.407E+00 ]
>> Gradient at Termination: 202.77880769948104
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_11/transport_1001_mesh_11/main_reg_transport_1001_mesh_11/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 12 of subject 1001
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_12/transport_1001_mesh_12/time_reg_transport_1001_mesh_12/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -6.185E+01 [ attachment = -5.769E+01 ; regularity = -4.161E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -4.376E+01 [ attachment = -3.562E+01 ; regularity = -8.140E+00 ]
>> Gradient at Termination: 365.91770910053947
>> CONVERGENCE: RELATIVE REDUCTION OF F <= FACTR*EPSMCH
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1001/transported_mesh_12/transport_1001_mesh_12/main_reg_transport_1001_mesh_12/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.738E+01 [ attachment = -7.475E+01 ; regularity = -2.263E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.735E+01 [ attachment = -3.150E+01 ; regularity = -2.585E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -4.585E+01 [ attachment = -1.769E+01 ; regularity = -2.816E+01 ]
>> Gradient at Termination: 621.9279546713285
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 0 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_0/transport_1004_mesh_0/time_reg_transport_1004_mesh_0/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
>> Gradient at Termination: 0.005132623804322436
>> ABNORMAL:
>> Estimation took: 00 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_0/transport_1004_mesh_0/main_reg_transport_1004_mesh_0/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 06 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 1 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_1/transport_1004_mesh_1/time_reg_transport_1004_mesh_1/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.256E+01 [ attachment = -2.919E+01 ; regularity = -3.372E+00 ]
>> Gradient at Termination: 445.4042237361798
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_1/transport_1004_mesh_1/main_reg_transport_1004_mesh_1/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 06 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 2 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_2/transport_1004_mesh_2/time_reg_transport_1004_mesh_2/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -4.849E+01 [ attachment = -3.759E+01 ; regularity = -1.089E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -3.745E+01 [ attachment = -2.453E+01 ; regularity = -1.292E+01 ]
>> Gradient at Termination: 188.79017746548902
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_2/transport_1004_mesh_2/main_reg_transport_1004_mesh_2/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 3 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_3/transport_1004_mesh_3/time_reg_transport_1004_mesh_3/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.998E+01 [ attachment = -2.603E+01 ; regularity = -3.946E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.057E+01 [ attachment = -1.378E+01 ; regularity = -6.786E+00 ]
>> Gradient at Termination: 397.51171665041926
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_3/transport_1004_mesh_3/main_reg_transport_1004_mesh_3/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 4 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_4/transport_1004_mesh_4/time_reg_transport_1004_mesh_4/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.831E+01 [ attachment = -2.494E+01 ; regularity = -3.375E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.142E+01 [ attachment = -1.634E+01 ; regularity = -5.078E+00 ]
>> Gradient at Termination: 93.82110241268228
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_4/transport_1004_mesh_4/main_reg_transport_1004_mesh_4/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 5 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_5/transport_1004_mesh_5/time_reg_transport_1004_mesh_5/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -4.202E+01 [ attachment = -3.841E+01 ; regularity = -3.619E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -3.393E+01 [ attachment = -2.925E+01 ; regularity = -4.679E+00 ]
>> Gradient at Termination: 166.2492326272927
>> CONVERGENCE: RELATIVE REDUCTION OF F <= FACTR*EPSMCH
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_5/transport_1004_mesh_5/main_reg_transport_1004_mesh_5/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 6 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_6/transport_1004_mesh_6/time_reg_transport_1004_mesh_6/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -5.156E+01 [ attachment = -4.478E+01 ; regularity = -6.781E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -3.530E+01 [ attachment = -2.394E+01 ; regularity = -1.136E+01 ]
>> Gradient at Termination: 296.5488552152031
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_6/transport_1004_mesh_6/main_reg_transport_1004_mesh_6/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 7 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_7/transport_1004_mesh_7/time_reg_transport_1004_mesh_7/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -4.153E+01 [ attachment = -3.494E+01 ; regularity = -6.591E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.940E+01 [ attachment = -2.053E+01 ; regularity = -8.866E+00 ]
>> Gradient at Termination: 216.02946341622837
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_7/transport_1004_mesh_7/main_reg_transport_1004_mesh_7/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 8 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_8/transport_1004_mesh_8/time_reg_transport_1004_mesh_8/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -5.801E+01 [ attachment = -4.581E+01 ; regularity = -1.220E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -4.189E+01 [ attachment = -2.603E+01 ; regularity = -1.586E+01 ]
>> Gradient at Termination: 162.7702172873855
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_8/transport_1004_mesh_8/main_reg_transport_1004_mesh_8/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 9 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_9/transport_1004_mesh_9/time_reg_transport_1004_mesh_9/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -1.907E+01 [ attachment = -1.262E+01 ; regularity = -6.442E+00 ]
>> Gradient at Termination: 147.37547085063028
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_9/transport_1004_mesh_9/main_reg_transport_1004_mesh_9/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 10 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_10/transport_1004_mesh_10/time_reg_transport_1004_mesh_10/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.788E+01 [ attachment = -3.125E+01 ; regularity = -6.625E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -2.672E+01 [ attachment = -1.753E+01 ; regularity = -9.188E+00 ]
>> Gradient at Termination: 170.18500893873448
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_10/transport_1004_mesh_10/main_reg_transport_1004_mesh_10/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 11 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_11/transport_1004_mesh_11/time_reg_transport_1004_mesh_11/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.416E+01 [ attachment = -1.812E+01 ; regularity = -6.031E+00 ]
>> Gradient at Termination: 85.32143940911217
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_11/transport_1004_mesh_11/main_reg_transport_1004_mesh_11/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 06 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 12 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_12/transport_1004_mesh_12/time_reg_transport_1004_mesh_12/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -5.173E+01 [ attachment = -4.309E+01 ; regularity = -8.633E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -3.668E+01 [ attachment = -2.403E+01 ; regularity = -1.264E+01 ]
>> Gradient at Termination: 146.4344191925134
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_12/transport_1004_mesh_12/main_reg_transport_1004_mesh_12/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 13 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_13/transport_1004_mesh_13/time_reg_transport_1004_mesh_13/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -9.966E+01 [ attachment = -7.981E+01 ; regularity = -1.985E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -6.833E+01 [ attachment = -4.503E+01 ; regularity = -2.330E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -5.816E+01 [ attachment = -3.081E+01 ; regularity = -2.735E+01 ]
>> Gradient at Termination: 178.59782696351252
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_13/transport_1004_mesh_13/main_reg_transport_1004_mesh_13/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 07 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 14 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_14/transport_1004_mesh_14/time_reg_transport_1004_mesh_14/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -5.823E+01 [ attachment = -4.569E+01 ; regularity = -1.254E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -4.222E+01 [ attachment = -2.572E+01 ; regularity = -1.650E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -3.795E+01 [ attachment = -2.031E+01 ; regularity = -1.764E+01 ]
>> Gradient at Termination: 71.70856788375427
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_14/transport_1004_mesh_14/main_reg_transport_1004_mesh_14/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 07 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 15 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_15/transport_1004_mesh_15/time_reg_transport_1004_mesh_15/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -3.817E+01 [ attachment = -2.969E+01 ; regularity = -8.487E+00 ]
>> Log-likelihood = -3.682E+01 [ attachment = -2.856E+01 ; regularity = -8.259E+00 ]
>> Gradient at Termination: 292.44666008645635
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_15/transport_1004_mesh_15/main_reg_transport_1004_mesh_15/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 07 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 16 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_16/transport_1004_mesh_16/time_reg_transport_1004_mesh_16/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -7.420E+01 [ attachment = -6.575E+01 ; regularity = -8.452E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -5.247E+01 [ attachment = -3.794E+01 ; regularity = -1.453E+01 ]
>> Gradient at Termination: 294.4958287728315
>> ABNORMAL:
>> Estimation took: 02 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_16/transport_1004_mesh_16/main_reg_transport_1004_mesh_16/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 17 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_17/transport_1004_mesh_17/time_reg_transport_1004_mesh_17/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -6.718E+01 [ attachment = -5.572E+01 ; regularity = -1.147E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -4.749E+01 [ attachment = -3.247E+01 ; regularity = -1.502E+01 ]
>> Gradient at Termination: 302.63267040997727
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_17/transport_1004_mesh_17/main_reg_transport_1004_mesh_17/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 06 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 18 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_18/transport_1004_mesh_18/time_reg_transport_1004_mesh_18/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -1.036E+02 [ attachment = -9.050E+01 ; regularity = -1.308E+01 ]
>> Log-likelihood = -9.095E+01 [ attachment = -8.006E+01 ; regularity = -1.088E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -6.290E+01 [ attachment = -4.422E+01 ; regularity = -1.869E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -5.419E+01 [ attachment = -3.216E+01 ; regularity = -2.204E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -4.895E+01 [ attachment = -2.578E+01 ; regularity = -2.317E+01 ]
>> Gradient at Termination: 103.81335171929831
>> ABNORMAL:
>> Estimation took: 05 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_18/transport_1004_mesh_18/main_reg_transport_1004_mesh_18/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 06 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 19 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_19/transport_1004_mesh_19/time_reg_transport_1004_mesh_19/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -6.265E+01 [ attachment = -5.669E+01 ; regularity = -5.965E+00 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -4.454E+01 [ attachment = -3.394E+01 ; regularity = -1.060E+01 ]
>> Gradient at Termination: 590.1930279261819
>> ABNORMAL:
>> Estimation took: 03 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_19/transport_1004_mesh_19/main_reg_transport_1004_mesh_19/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 07 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
transporting mesh 20 of subject 1004
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_20/transport_1004_mesh_20/time_reg_transport_1004_mesh_20/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 30 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -1.065E+02 [ attachment = -9.409E+01 ; regularity = -1.242E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -7.480E+01 [ attachment = -5.094E+01 ; regularity = -2.386E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -6.924E+01 [ attachment = -4.234E+01 ; regularity = -2.690E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -6.485E+01 [ attachment = -3.806E+01 ; regularity = -2.679E+01 ]
>> Gradient at Termination: 98.50229574146769
>> ABNORMAL:
>> Estimation took: 04 seconds
Deformetrica.__del__()
Logger has been set to: DEBUG
>> No initial CP spacing given: using diffeo kernel width of 10
OMP_NUM_THREADS was not found in environment variables. An automatic value will be set.
OMP_NUM_THREADS will be set to 128
context has already been set
>> No specified state-file. By default, Deformetrica state will by saved in file: results/transports/1004/transported_mesh_20/transport_1004_mesh_20/main_reg_transport_1004_mesh_20/deformetrica-state.p.
>> Using a Sobolev gradient for the template data with the ScipyLBFGS estimator memory length being larger than 1. Beware: that can be tricky.
>> Set of 24 control points defined.
>> Momenta initialized to zero, for 1 subjects.
dtype=float32
>> Started estimator: ScipyOptimize
>> Scipy optimization method: L-BFGS-B
------------------------------------- Iteration: 1 -------------------------------------
------------------------------------- Iteration: 20 -------------------------------------
>> Log-likelihood = -2.396E+02 [ attachment = -1.732E+02 ; regularity = -6.633E+01 ]
------------------------------------- Iteration: 40 -------------------------------------
>> Log-likelihood = -1.808E+02 [ attachment = -1.082E+02 ; regularity = -7.259E+01 ]
------------------------------------- Iteration: 60 -------------------------------------
>> Log-likelihood = -1.629E+02 [ attachment = -8.822E+01 ; regularity = -7.466E+01 ]
------------------------------------- Iteration: 80 -------------------------------------
>> Log-likelihood = -1.557E+02 [ attachment = -7.484E+01 ; regularity = -8.088E+01 ]
------------------------------------- Iteration: 100 -------------------------------------
>> Log-likelihood = -1.526E+02 [ attachment = -6.912E+01 ; regularity = -8.351E+01 ]
>> Gradient at Termination: 796.8639724127695
>> ABNORMAL:
>> Estimation took: 07 seconds
Deformetrica.__del__()
Logger has been set to: INFO
In exponential update, I am not flowing because I don't have any template points to flow
In exponential update, I am not flowing because I don't have any template points to flow
[13]:
# Check that control points are the same across subjects
pl = pv.Plotter(shape=(1, 3), border=False, window_size=[1200, 300])
for i, subject_id in enumerate(SUBJECT_IDS):
pl.subplot(0, i)
pl.add_mesh(templates["global"], show_edges=True)
cps = pv.PolyData(control_points[subject_id][0].cpu().numpy())
pl.add_mesh(cps)
# Add arrows at control points showing momenta
# cps["vectors"] = momenta[subject_id][0].cpu().numpy()
# pl.add_mesh(cps.glyph(orient="vectors", scale=False, factor=2),
# color="red", opacity=0.8)
pl.add_text(
f"deformation of first mesh of {subject_id} on global template",
position="upper_edge",
font_size=4,
)
pl.show()
# Check that momenta are the same across subjects
/home/nmiolane/anaconda3/envs/polpo/lib/python3.11/site-packages/pyvista/jupyter/notebook.py:56: UserWarning: Failed to use notebook backend:
No module named 'trame'
Falling back to a static output.
warnings.warn(
[ ]:
from sklearn.linear_model import LinearRegression
X = []
y = []
for subject_id in SUBJECT_IDS:
# Get pregnancy indices from CSV files
subject_csv = csvs[subject_id]
subject_momenta = momenta[subject_id]
assert len(subject_momenta) == len(subject_csv)
pregnancy_indices = subject_csv.reset_index().index[subject_csv["stage"] == "preg"]
# Select corresponding pre-pregnancy meshes
pregnancy_momenta = [subject_momenta[i] for i in pregnancy_indices]
pregnancy_gestweek = subject_csv["gestWeek"][
subject_csv["stage"] == "preg"
].tolist()
assert len(pregnancy_gestweek) == len(pregnancy_momenta)
print(f"Found {len(pregnancy_momenta)} pregnancy momenta")
y.extend(pregnancy_gestweek)
X.extend(pregnancy_momenta)
X = np.array(X).reshape(len(y), -1)
y = np.array(y)
# Standardize y to have zero mean and unit variance
y = (y - np.mean(y)) / np.std(y)
print(X.shape)
print(y.shape)
Found 7 pregnancy momenta
Found 14 pregnancy momenta
(21, 72)
(21,)
[ ]:
# Train-test split and regression
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=42
)
regression = LinearRegression()
regression.fit(X_train, y_train)
train_r2 = regression.score(X_train, y_train)
test_r2 = regression.score(X_test, y_test)
print(f"Regression coefficients: {regression.coef_}")
print(f"Regression intercept: {regression.intercept_}")
print(f"Train R2 score: {train_r2:.3f}")
print(f"Test R2 score: {test_r2:.3f}")
Regression coefficients: [-0.0475128 -0.20793428 0.12518647 -0.40066458 -0.30088703 0.13057257
0.11033436 0.17746964 0.16130291 0.37172321 0.04971518 -0.1947087
0.00707097 0.04679694 -0.14465205 -0.06615254 0.02296597 -0.03906212
-0.15404887 -0.09492599 -0.08598621 -0.20808952 0.1928069 0.20513928
0.08681601 0.01675351 -0.04860588 0.05266796 -0.14478317 0.02885679
-0.03100625 0.04538691 -0.10291122 -0.00315975 -0.10886183 0.15149466
0.0970834 -0.0382668 0.08020802 -0.11975142 0.10791238 -0.13274261
0.02983922 -0.14670629 0.0763163 0.11544306 0.00725577 -0.02045337
0.09999708 -0.0052859 0.12839739 -0.02726886 0.07361428 -0.146344
0.12439884 -0.17373766 -0.12048952 0.18532592 -0.20879205 -0.03906035
-0.13822599 0.16314038 -0.00389031 0.09263556 -0.0472091 0.04504123
-0.04774953 0.03857911 0.09940681 -0.03347729 -0.11363047 -0.09416703]
Regression intercept: 0.5789366094388145
Train R2 score: 1.000
Test R2 score: -1.999
[ ]: