Instructions to use VBoussot/ImpactReg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KonfAI
How to use VBoussot/ImpactReg with KonfAI:
pip install "konfai[imaging]" konfai-apps
# List the apps this repository holds konfai-apps list VBoussot/ImpactReg # Run one of them on an image konfai-apps infer VBoussot/ImpactReg:<app> -i image.nii.gz -o Output
- Notebooks
- Google Colab
- Kaggle
refactor(convexadam): scope the legacy-JIT-executor workaround to the registration
Browse filesReplace the module-import global torch JIT flag (which would impose the legacy executor on every itk-impact / torch user in the process) with a scoped _legacy_jit_executor() context manager around the registration run, restoring the caller's setting on exit. The proper fix belongs in itk-impact's C++ TorchScript execution; this is the bundle-side stopgap.
ConvexAdam_Coarse/Model.py
CHANGED
|
@@ -33,6 +33,7 @@ NOTE: do NOT add ``from __future__ import annotations`` — KonfAI's config engi
|
|
| 33 |
runtime-evaluated annotations (``get_origin``); PEP 563 stringized annotations break binding.
|
| 34 |
"""
|
| 35 |
|
|
|
|
| 36 |
import json
|
| 37 |
import os
|
| 38 |
from dataclasses import dataclass, field
|
|
@@ -49,13 +50,6 @@ from konfai.network import network
|
|
| 49 |
from konfai.utils.config import Choices, Range
|
| 50 |
from konfai.utils.dataset import Attribute, data_to_image, image_to_data
|
| 51 |
|
| 52 |
-
# Some TorchScript feature models (notably the TS segmentation exports) trip the JIT TensorExpr fuser's alias
|
| 53 |
-
# analysis ("INTERNAL ASSERT FAILED ... We don't have an op for aten::dim") when itk-impact runs them through
|
| 54 |
-
# libtorch. Fall back to the stable legacy executor (no profiling / no fusion) so every registry model runs;
|
| 55 |
-
# itk-impact shares Python's libtorch, so setting the global flag here also applies to its C++ execution.
|
| 56 |
-
torch._C._jit_set_profiling_executor(False)
|
| 57 |
-
torch._C._jit_set_profiling_mode(False)
|
| 58 |
-
|
| 59 |
DIM = 3
|
| 60 |
# The feature model's input channel count is an intrinsic property of the pretrained model (grayscale
|
| 61 |
# medical images), not a tunable — so it's fixed here, never a config/signature parameter.
|
|
@@ -113,6 +107,21 @@ class ModelSpec:
|
|
| 113 |
distance: Literal["L1", "L2", "Dice", "Cosine", "NCC"] = "L1"
|
| 114 |
|
| 115 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
def _coarse_registration_type():
|
| 117 |
"""The coupled-convex initializer, tolerant to the two names the wrapping has shipped under."""
|
| 118 |
cls = getattr(itk, "ImpactCoarseRegistration", None) or getattr(itk, "ImpactConvexAdamInitializer", None)
|
|
@@ -451,7 +460,7 @@ class ConvexAdamRegistration(torch.nn.Module):
|
|
| 451 |
# ConvexAdam runs a gradient-based instance optimisation (Adam over the field) inside itk-impact's
|
| 452 |
# .Update(); the predictor calls forward under torch.inference_mode(), which forbids autograd. The
|
| 453 |
# image tensors have already crossed to numpy/ITK here, so re-enable grad for the optimisation.
|
| 454 |
-
with torch.inference_mode(False), torch.enable_grad():
|
| 455 |
for b in range(fixed.shape[0]):
|
| 456 |
fixed_img = data_to_image(fixed[b].detach().cpu().numpy(), fixed_attrs[b])
|
| 457 |
moving_img = data_to_image(moving[b].detach().cpu().numpy(), moving_attrs[b])
|
|
|
|
| 33 |
runtime-evaluated annotations (``get_origin``); PEP 563 stringized annotations break binding.
|
| 34 |
"""
|
| 35 |
|
| 36 |
+
import contextlib
|
| 37 |
import json
|
| 38 |
import os
|
| 39 |
from dataclasses import dataclass, field
|
|
|
|
| 50 |
from konfai.utils.config import Choices, Range
|
| 51 |
from konfai.utils.dataset import Attribute, data_to_image, image_to_data
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
DIM = 3
|
| 54 |
# The feature model's input channel count is an intrinsic property of the pretrained model (grayscale
|
| 55 |
# medical images), not a tunable — so it's fixed here, never a config/signature parameter.
|
|
|
|
| 107 |
distance: Literal["L1", "L2", "Dice", "Cosine", "NCC"] = "L1"
|
| 108 |
|
| 109 |
|
| 110 |
+
@contextlib.contextmanager
|
| 111 |
+
def _legacy_jit_executor():
|
| 112 |
+
"""Run TorchScript feature models on torch's stable legacy executor (no profiling / TensorExpr fusion) for
|
| 113 |
+
the duration of the block: some models (the TS segmentation exports) crash the fuser ("aten::dim" internal
|
| 114 |
+
assert) when itk-impact runs them through libtorch. Strictly SCOPED — the caller's global JIT settings are
|
| 115 |
+
restored on exit, so nothing is imposed on other itk-impact / torch users in the process."""
|
| 116 |
+
old_executor = torch._C._jit_set_profiling_executor(False)
|
| 117 |
+
old_mode = torch._C._jit_set_profiling_mode(False)
|
| 118 |
+
try:
|
| 119 |
+
yield
|
| 120 |
+
finally:
|
| 121 |
+
torch._C._jit_set_profiling_executor(old_executor)
|
| 122 |
+
torch._C._jit_set_profiling_mode(old_mode)
|
| 123 |
+
|
| 124 |
+
|
| 125 |
def _coarse_registration_type():
|
| 126 |
"""The coupled-convex initializer, tolerant to the two names the wrapping has shipped under."""
|
| 127 |
cls = getattr(itk, "ImpactCoarseRegistration", None) or getattr(itk, "ImpactConvexAdamInitializer", None)
|
|
|
|
| 460 |
# ConvexAdam runs a gradient-based instance optimisation (Adam over the field) inside itk-impact's
|
| 461 |
# .Update(); the predictor calls forward under torch.inference_mode(), which forbids autograd. The
|
| 462 |
# image tensors have already crossed to numpy/ITK here, so re-enable grad for the optimisation.
|
| 463 |
+
with torch.inference_mode(False), torch.enable_grad(), _legacy_jit_executor():
|
| 464 |
for b in range(fixed.shape[0]):
|
| 465 |
fixed_img = data_to_image(fixed[b].detach().cpu().numpy(), fixed_attrs[b])
|
| 466 |
moving_img = data_to_image(moving[b].detach().cpu().numpy(), moving_attrs[b])
|
ConvexAdam_Coarse/__pycache__/Model.cpython-313.pyc
CHANGED
|
Binary files a/ConvexAdam_Coarse/__pycache__/Model.cpython-313.pyc and b/ConvexAdam_Coarse/__pycache__/Model.cpython-313.pyc differ
|
|
|
ConvexAdam_Composite/Model.py
CHANGED
|
@@ -33,6 +33,7 @@ NOTE: do NOT add ``from __future__ import annotations`` — KonfAI's config engi
|
|
| 33 |
runtime-evaluated annotations (``get_origin``); PEP 563 stringized annotations break binding.
|
| 34 |
"""
|
| 35 |
|
|
|
|
| 36 |
import json
|
| 37 |
import os
|
| 38 |
from dataclasses import dataclass, field
|
|
@@ -49,13 +50,6 @@ from konfai.network import network
|
|
| 49 |
from konfai.utils.config import Choices, Range
|
| 50 |
from konfai.utils.dataset import Attribute, data_to_image, image_to_data
|
| 51 |
|
| 52 |
-
# Some TorchScript feature models (notably the TS segmentation exports) trip the JIT TensorExpr fuser's alias
|
| 53 |
-
# analysis ("INTERNAL ASSERT FAILED ... We don't have an op for aten::dim") when itk-impact runs them through
|
| 54 |
-
# libtorch. Fall back to the stable legacy executor (no profiling / no fusion) so every registry model runs;
|
| 55 |
-
# itk-impact shares Python's libtorch, so setting the global flag here also applies to its C++ execution.
|
| 56 |
-
torch._C._jit_set_profiling_executor(False)
|
| 57 |
-
torch._C._jit_set_profiling_mode(False)
|
| 58 |
-
|
| 59 |
DIM = 3
|
| 60 |
# The feature model's input channel count is an intrinsic property of the pretrained model (grayscale
|
| 61 |
# medical images), not a tunable — so it's fixed here, never a config/signature parameter.
|
|
@@ -113,6 +107,21 @@ class ModelSpec:
|
|
| 113 |
distance: Literal["L1", "L2", "Dice", "Cosine", "NCC"] = "L1"
|
| 114 |
|
| 115 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
def _coarse_registration_type():
|
| 117 |
"""The coupled-convex initializer, tolerant to the two names the wrapping has shipped under."""
|
| 118 |
cls = getattr(itk, "ImpactCoarseRegistration", None) or getattr(itk, "ImpactConvexAdamInitializer", None)
|
|
@@ -451,7 +460,7 @@ class ConvexAdamRegistration(torch.nn.Module):
|
|
| 451 |
# ConvexAdam runs a gradient-based instance optimisation (Adam over the field) inside itk-impact's
|
| 452 |
# .Update(); the predictor calls forward under torch.inference_mode(), which forbids autograd. The
|
| 453 |
# image tensors have already crossed to numpy/ITK here, so re-enable grad for the optimisation.
|
| 454 |
-
with torch.inference_mode(False), torch.enable_grad():
|
| 455 |
for b in range(fixed.shape[0]):
|
| 456 |
fixed_img = data_to_image(fixed[b].detach().cpu().numpy(), fixed_attrs[b])
|
| 457 |
moving_img = data_to_image(moving[b].detach().cpu().numpy(), moving_attrs[b])
|
|
|
|
| 33 |
runtime-evaluated annotations (``get_origin``); PEP 563 stringized annotations break binding.
|
| 34 |
"""
|
| 35 |
|
| 36 |
+
import contextlib
|
| 37 |
import json
|
| 38 |
import os
|
| 39 |
from dataclasses import dataclass, field
|
|
|
|
| 50 |
from konfai.utils.config import Choices, Range
|
| 51 |
from konfai.utils.dataset import Attribute, data_to_image, image_to_data
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
DIM = 3
|
| 54 |
# The feature model's input channel count is an intrinsic property of the pretrained model (grayscale
|
| 55 |
# medical images), not a tunable — so it's fixed here, never a config/signature parameter.
|
|
|
|
| 107 |
distance: Literal["L1", "L2", "Dice", "Cosine", "NCC"] = "L1"
|
| 108 |
|
| 109 |
|
| 110 |
+
@contextlib.contextmanager
|
| 111 |
+
def _legacy_jit_executor():
|
| 112 |
+
"""Run TorchScript feature models on torch's stable legacy executor (no profiling / TensorExpr fusion) for
|
| 113 |
+
the duration of the block: some models (the TS segmentation exports) crash the fuser ("aten::dim" internal
|
| 114 |
+
assert) when itk-impact runs them through libtorch. Strictly SCOPED — the caller's global JIT settings are
|
| 115 |
+
restored on exit, so nothing is imposed on other itk-impact / torch users in the process."""
|
| 116 |
+
old_executor = torch._C._jit_set_profiling_executor(False)
|
| 117 |
+
old_mode = torch._C._jit_set_profiling_mode(False)
|
| 118 |
+
try:
|
| 119 |
+
yield
|
| 120 |
+
finally:
|
| 121 |
+
torch._C._jit_set_profiling_executor(old_executor)
|
| 122 |
+
torch._C._jit_set_profiling_mode(old_mode)
|
| 123 |
+
|
| 124 |
+
|
| 125 |
def _coarse_registration_type():
|
| 126 |
"""The coupled-convex initializer, tolerant to the two names the wrapping has shipped under."""
|
| 127 |
cls = getattr(itk, "ImpactCoarseRegistration", None) or getattr(itk, "ImpactConvexAdamInitializer", None)
|
|
|
|
| 460 |
# ConvexAdam runs a gradient-based instance optimisation (Adam over the field) inside itk-impact's
|
| 461 |
# .Update(); the predictor calls forward under torch.inference_mode(), which forbids autograd. The
|
| 462 |
# image tensors have already crossed to numpy/ITK here, so re-enable grad for the optimisation.
|
| 463 |
+
with torch.inference_mode(False), torch.enable_grad(), _legacy_jit_executor():
|
| 464 |
for b in range(fixed.shape[0]):
|
| 465 |
fixed_img = data_to_image(fixed[b].detach().cpu().numpy(), fixed_attrs[b])
|
| 466 |
moving_img = data_to_image(moving[b].detach().cpu().numpy(), moving_attrs[b])
|
ConvexAdam_Composite/__pycache__/Model.cpython-313.pyc
CHANGED
|
Binary files a/ConvexAdam_Composite/__pycache__/Model.cpython-313.pyc and b/ConvexAdam_Composite/__pycache__/Model.cpython-313.pyc differ
|
|
|
ConvexAdam_Fine/Model.py
CHANGED
|
@@ -33,6 +33,7 @@ NOTE: do NOT add ``from __future__ import annotations`` — KonfAI's config engi
|
|
| 33 |
runtime-evaluated annotations (``get_origin``); PEP 563 stringized annotations break binding.
|
| 34 |
"""
|
| 35 |
|
|
|
|
| 36 |
import json
|
| 37 |
import os
|
| 38 |
from dataclasses import dataclass, field
|
|
@@ -49,13 +50,6 @@ from konfai.network import network
|
|
| 49 |
from konfai.utils.config import Choices, Range
|
| 50 |
from konfai.utils.dataset import Attribute, data_to_image, image_to_data
|
| 51 |
|
| 52 |
-
# Some TorchScript feature models (notably the TS segmentation exports) trip the JIT TensorExpr fuser's alias
|
| 53 |
-
# analysis ("INTERNAL ASSERT FAILED ... We don't have an op for aten::dim") when itk-impact runs them through
|
| 54 |
-
# libtorch. Fall back to the stable legacy executor (no profiling / no fusion) so every registry model runs;
|
| 55 |
-
# itk-impact shares Python's libtorch, so setting the global flag here also applies to its C++ execution.
|
| 56 |
-
torch._C._jit_set_profiling_executor(False)
|
| 57 |
-
torch._C._jit_set_profiling_mode(False)
|
| 58 |
-
|
| 59 |
DIM = 3
|
| 60 |
# The feature model's input channel count is an intrinsic property of the pretrained model (grayscale
|
| 61 |
# medical images), not a tunable — so it's fixed here, never a config/signature parameter.
|
|
@@ -113,6 +107,21 @@ class ModelSpec:
|
|
| 113 |
distance: Literal["L1", "L2", "Dice", "Cosine", "NCC"] = "L1"
|
| 114 |
|
| 115 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
def _coarse_registration_type():
|
| 117 |
"""The coupled-convex initializer, tolerant to the two names the wrapping has shipped under."""
|
| 118 |
cls = getattr(itk, "ImpactCoarseRegistration", None) or getattr(itk, "ImpactConvexAdamInitializer", None)
|
|
@@ -451,7 +460,7 @@ class ConvexAdamRegistration(torch.nn.Module):
|
|
| 451 |
# ConvexAdam runs a gradient-based instance optimisation (Adam over the field) inside itk-impact's
|
| 452 |
# .Update(); the predictor calls forward under torch.inference_mode(), which forbids autograd. The
|
| 453 |
# image tensors have already crossed to numpy/ITK here, so re-enable grad for the optimisation.
|
| 454 |
-
with torch.inference_mode(False), torch.enable_grad():
|
| 455 |
for b in range(fixed.shape[0]):
|
| 456 |
fixed_img = data_to_image(fixed[b].detach().cpu().numpy(), fixed_attrs[b])
|
| 457 |
moving_img = data_to_image(moving[b].detach().cpu().numpy(), moving_attrs[b])
|
|
|
|
| 33 |
runtime-evaluated annotations (``get_origin``); PEP 563 stringized annotations break binding.
|
| 34 |
"""
|
| 35 |
|
| 36 |
+
import contextlib
|
| 37 |
import json
|
| 38 |
import os
|
| 39 |
from dataclasses import dataclass, field
|
|
|
|
| 50 |
from konfai.utils.config import Choices, Range
|
| 51 |
from konfai.utils.dataset import Attribute, data_to_image, image_to_data
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
DIM = 3
|
| 54 |
# The feature model's input channel count is an intrinsic property of the pretrained model (grayscale
|
| 55 |
# medical images), not a tunable — so it's fixed here, never a config/signature parameter.
|
|
|
|
| 107 |
distance: Literal["L1", "L2", "Dice", "Cosine", "NCC"] = "L1"
|
| 108 |
|
| 109 |
|
| 110 |
+
@contextlib.contextmanager
|
| 111 |
+
def _legacy_jit_executor():
|
| 112 |
+
"""Run TorchScript feature models on torch's stable legacy executor (no profiling / TensorExpr fusion) for
|
| 113 |
+
the duration of the block: some models (the TS segmentation exports) crash the fuser ("aten::dim" internal
|
| 114 |
+
assert) when itk-impact runs them through libtorch. Strictly SCOPED — the caller's global JIT settings are
|
| 115 |
+
restored on exit, so nothing is imposed on other itk-impact / torch users in the process."""
|
| 116 |
+
old_executor = torch._C._jit_set_profiling_executor(False)
|
| 117 |
+
old_mode = torch._C._jit_set_profiling_mode(False)
|
| 118 |
+
try:
|
| 119 |
+
yield
|
| 120 |
+
finally:
|
| 121 |
+
torch._C._jit_set_profiling_executor(old_executor)
|
| 122 |
+
torch._C._jit_set_profiling_mode(old_mode)
|
| 123 |
+
|
| 124 |
+
|
| 125 |
def _coarse_registration_type():
|
| 126 |
"""The coupled-convex initializer, tolerant to the two names the wrapping has shipped under."""
|
| 127 |
cls = getattr(itk, "ImpactCoarseRegistration", None) or getattr(itk, "ImpactConvexAdamInitializer", None)
|
|
|
|
| 460 |
# ConvexAdam runs a gradient-based instance optimisation (Adam over the field) inside itk-impact's
|
| 461 |
# .Update(); the predictor calls forward under torch.inference_mode(), which forbids autograd. The
|
| 462 |
# image tensors have already crossed to numpy/ITK here, so re-enable grad for the optimisation.
|
| 463 |
+
with torch.inference_mode(False), torch.enable_grad(), _legacy_jit_executor():
|
| 464 |
for b in range(fixed.shape[0]):
|
| 465 |
fixed_img = data_to_image(fixed[b].detach().cpu().numpy(), fixed_attrs[b])
|
| 466 |
moving_img = data_to_image(moving[b].detach().cpu().numpy(), moving_attrs[b])
|
ConvexAdam_Fine/__pycache__/Model.cpython-313.pyc
CHANGED
|
Binary files a/ConvexAdam_Fine/__pycache__/Model.cpython-313.pyc and b/ConvexAdam_Fine/__pycache__/Model.cpython-313.pyc differ
|
|
|