monai-weekly 1.4.dev2440__py3-none-any.whl → 1.5.dev2442__py3-none-any.whl

monai/__init__.py

@@ -136,4 +136,4 @@ except BaseException:
 
     if MONAIEnvVars.debug():
         raise
-__commit_id__ = "76ef9f40c8da626928238c91eacddc789b0b4530"
+__commit_id__ = "a14a9d77165b11996c023a9bf8e649c3c5d6bbbc"

monai/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2024-10-06T02:29:02+0000",
+ "date": "2024-10-20T02:29:48+0000",
  "dirty": false,
  "error": null,
- "full-revisionid": "c2bfe29203f3a82b689d3f1d5334e484f6fbb1a6",
- "version": "1.4.dev2440"
+ "full-revisionid": "d850fe3e5160f867a27d3f9e45f7ca1e4c7e53e5",
+ "version": "1.5.dev2442"
 }
 '''  # END VERSION_JSON
 

monai/apps/deepgrow/transforms.py

@@ -803,6 +803,14 @@ class RestoreLabeld(MapTransform):
         original_shape_key: key that records original shape for foreground.
         cropped_shape_key: key that records cropped shape for foreground.
         allow_missing_keys: don't raise exception if key is missing.
+        restore_resizing: used to enable or disable resizing restoration, default is True.
+            If True, the transform will resize the items back to its original shape.
+        restore_cropping: used to enable or disable cropping restoration, default is True.
+            If True, the transform will restore the items to its uncropped size.
+        restore_spacing: used to enable or disable spacing restoration, default is True.
+            If True, the transform will resample the items back to the spacing it had before being altered.
+        restore_slicing: used to enable or disable slicing restoration, default is True.
+            If True, the transform will reassemble the full volume by restoring the slices to their original positions.
     """
 
     def __init__(
@@ -819,6 +827,10 @@ class RestoreLabeld(MapTransform):
         original_shape_key: str = "foreground_original_shape",
         cropped_shape_key: str = "foreground_cropped_shape",
         allow_missing_keys: bool = False,
+        restore_resizing: bool = True,
+        restore_cropping: bool = True,
+        restore_spacing: bool = True,
+        restore_slicing: bool = True,
     ) -> None:
         super().__init__(keys, allow_missing_keys)
         self.ref_image = ref_image
@@ -833,6 +845,10 @@ class RestoreLabeld(MapTransform):
         self.end_coord_key = end_coord_key
         self.original_shape_key = original_shape_key
         self.cropped_shape_key = cropped_shape_key
+        self.restore_resizing = restore_resizing
+        self.restore_cropping = restore_cropping
+        self.restore_spacing = restore_spacing
+        self.restore_slicing = restore_slicing
 
     def __call__(self, data: Any) -> dict:
         d = dict(data)
@@ -842,38 +858,45 @@ class RestoreLabeld(MapTransform):
             image = d[key]
 
             # Undo Resize
-            current_shape = image.shape
-            cropped_shape = meta_dict[self.cropped_shape_key]
-            if np.any(np.not_equal(current_shape, cropped_shape)):
-                resizer = Resize(spatial_size=cropped_shape[1:], mode=mode)
-                image = resizer(image, mode=mode, align_corners=align_corners)
+            if self.restore_resizing:
+                current_shape = image.shape
+                cropped_shape = meta_dict[self.cropped_shape_key]
+                if np.any(np.not_equal(current_shape, cropped_shape)):
+                    resizer = Resize(spatial_size=cropped_shape[1:], mode=mode)
+                    image = resizer(image, mode=mode, align_corners=align_corners)
 
             # Undo Crop
-            original_shape = meta_dict[self.original_shape_key]
-            result = np.zeros(original_shape, dtype=np.float32)
-            box_start = meta_dict[self.start_coord_key]
-            box_end = meta_dict[self.end_coord_key]
-
-            spatial_dims = min(len(box_start), len(image.shape[1:]))
-            slices = tuple(
-                [slice(None)] + [slice(s, e) for s, e in zip(box_start[:spatial_dims], box_end[:spatial_dims])]
-            )
-            result[slices] = image
+            if self.restore_cropping:
+                original_shape = meta_dict[self.original_shape_key]
+                result = np.zeros(original_shape, dtype=np.float32)
+                box_start = meta_dict[self.start_coord_key]
+                box_end = meta_dict[self.end_coord_key]
+
+                spatial_dims = min(len(box_start), len(image.shape[1:]))
+                slices = tuple(
+                    [slice(None)] + [slice(s, e) for s, e in zip(box_start[:spatial_dims], box_end[:spatial_dims])]
+                )
+                result[slices] = image
+            else:
+                result = image
 
             # Undo Spacing
-            current_size = result.shape[1:]
-            # change spatial_shape from HWD to DHW
-            spatial_shape = list(np.roll(meta_dict["spatial_shape"], 1))
-            spatial_size = spatial_shape[-len(current_size) :]
+            if self.restore_spacing:
+                current_size = result.shape[1:]
+                # change spatial_shape from HWD to DHW
+                spatial_shape = list(np.roll(meta_dict["spatial_shape"], 1))
+                spatial_size = spatial_shape[-len(current_size) :]
 
-            if np.any(np.not_equal(current_size, spatial_size)):
-                resizer = Resize(spatial_size=spatial_size, mode=mode)
-                result = resizer(result, mode=mode, align_corners=align_corners)  # type: ignore
+                if np.any(np.not_equal(current_size, spatial_size)):
+                    resizer = Resize(spatial_size=spatial_size, mode=mode)
+                    result = resizer(result, mode=mode, align_corners=align_corners)  # type: ignore
 
             # Undo Slicing
             slice_idx = meta_dict.get("slice_idx")
             final_result: NdarrayOrTensor
-            if slice_idx is None or self.slice_only:
+            if not self.restore_slicing:  # do nothing if restore slicing isn't requested
+                final_result = result
+            elif slice_idx is None or self.slice_only:
                 final_result = result if len(result.shape) <= 3 else result[0]
             else:
                 slice_idx = meta_dict["slice_idx"][0]

monai/networks/schedulers/ddim.py

@@ -220,7 +220,7 @@ class DDIMScheduler(Scheduler):
         if eta > 0:
             # randn_like does not support generator https://github.com/pytorch/pytorch/issues/27072
             device: torch.device = torch.device(model_output.device if torch.is_tensor(model_output) else "cpu")
-            noise = torch.randn(model_output.shape, dtype=model_output.dtype, generator=generator).to(device)
+            noise = torch.randn(model_output.shape, dtype=model_output.dtype, generator=generator, device=device)
             variance = self._get_variance(timestep, prev_timestep) ** 0.5 * eta * noise
 
             pred_prev_sample = pred_prev_sample + variance

monai/networks/schedulers/ddpm.py

@@ -241,8 +241,12 @@ class DDPMScheduler(Scheduler):
         variance = 0
         if timestep > 0:
             noise = torch.randn(
-                model_output.size(), dtype=model_output.dtype, layout=model_output.layout, generator=generator
-            ).to(model_output.device)
+                model_output.size(),
+                dtype=model_output.dtype,
+                layout=model_output.layout,
+                generator=generator,
+                device=model_output.device,
+            )
             variance = (self._get_variance(timestep, predicted_variance=predicted_variance) ** 0.5) * noise
 
         pred_prev_sample = pred_prev_sample + variance

monai/transforms/regularization/array.py

@@ -112,6 +112,11 @@ class CutMix(Mixer):
         the mixing weight but also the size of the random rectangles used during for mixing.
         Please refer to the paper for details.
 
+        Please note that there is a change in behavior starting from version 1.4.0. In the previous
+        implementation, the transform would generate a different label each time it was called.
+        To ensure determinism, the new implementation will now generate the same label for
+        the same input image when using the same operation.
+
         The most common use case is something close to:
 
     .. code-block:: python

{monai_weekly-1.4.dev2440.dist-info → monai_weekly-1.5.dev2442.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: monai-weekly
-Version: 1.4.dev2440
+Version: 1.5.dev2442
 Summary: AI Toolkit for Healthcare Imaging
 Home-page: https://monai.io/
 Author: MONAI Consortium
@@ -171,11 +171,11 @@ Requires-Dist: zarr; extra == "zarr"
 [![codecov](https://codecov.io/gh/Project-MONAI/MONAI/branch/dev/graph/badge.svg?token=6FTC7U1JJ4)](https://codecov.io/gh/Project-MONAI/MONAI)
 [![monai Downloads Last Month](https://assets.piptrends.com/get-last-month-downloads-badge/monai.svg 'monai Downloads Last Month by pip Trends')](https://piptrends.com/package/monai)
 
-MONAI is a [PyTorch](https://pytorch.org/)-based, [open-source](https://github.com/Project-MONAI/MONAI/blob/dev/LICENSE) framework for deep learning in healthcare imaging, part of [PyTorch Ecosystem](https://pytorch.org/ecosystem/).
-Its ambitions are:
-- developing a community of academic, industrial and clinical researchers collaborating on a common foundation;
-- creating state-of-the-art, end-to-end training workflows for healthcare imaging;
-- providing researchers with the optimized and standardized way to create and evaluate deep learning models.
+MONAI is a [PyTorch](https://pytorch.org/)-based, [open-source](https://github.com/Project-MONAI/MONAI/blob/dev/LICENSE) framework for deep learning in healthcare imaging, part of the [PyTorch Ecosystem](https://pytorch.org/ecosystem/).
+Its ambitions are as follows:
+- Developing a community of academic, industrial and clinical researchers collaborating on a common foundation;
+- Creating state-of-the-art, end-to-end training workflows for healthcare imaging;
+- Providing researchers with the optimized and standardized way to create and evaluate deep learning models.
 
 
 ## Features

{monai_weekly-1.4.dev2440.dist-info → monai_weekly-1.5.dev2442.dist-info}/RECORD

@@ -1,5 +1,5 @@
-monai/__init__.py,sha256=3xB7PrwYLHggh2WFpNAbzY3MQqA0crXLlS8jNEWtecw,4095
-monai/_version.py,sha256=-ga-_qWT6XVACl55eNJjoMaOVXleLJpCWK4Goh4e1BI,503
+monai/__init__.py,sha256=Pq8CvtjSIIpM46e3BgLQoDLKxCuHcP-V20mBqi5EA78,4095
+monai/_version.py,sha256=2XTx0tN1SVpKgJ5hNz8ZFMQ6-HRSmdB6OUfhWAZQmUY,503
 monai/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 monai/_extensions/__init__.py,sha256=NEBPreRhQ8H9gVvgrLr_y52_TmqB96u_u4VQmeNT93I,642
 monai/_extensions/loader.py,sha256=7SiKw36q-nOzH8CRbBurFrz7GM40GCu7rc93Tm8XpnI,3643
@@ -26,7 +26,7 @@ monai/apps/deepedit/transforms.py,sha256=Udj35m10Irek5Gtqo6Hgv6Lt7S6jSo-z0NuyVbs
 monai/apps/deepgrow/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJr4ZZJZLq0,573
 monai/apps/deepgrow/dataset.py,sha256=W0wv1QujA4sZgrAcBS64dl3OBbDBM2cF4RK0fDCQnRU,10054
 monai/apps/deepgrow/interaction.py,sha256=-smtOl93i_SDEo_Yo8DE5U3FnDrUcdJWeP14nCq5GS4,3748
-monai/apps/deepgrow/transforms.py,sha256=MQ3WPGfqagXoN6ySccpPFWOQAcxKOX4VUeQ0Zybx45I,41873
+monai/apps/deepgrow/transforms.py,sha256=RmKMoN4sqhT84ognTJt55t6UtkL_OpkzRcP5VPseSss,43349
 monai/apps/detection/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJr4ZZJZLq0,573
 monai/apps/detection/metrics/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJr4ZZJZLq0,573
 monai/apps/detection/metrics/coco.py,sha256=bpF6hAAMKsBNLfat-Fzh0CR-0swDsAAVcwTaZ-lo1_g,26618
@@ -336,8 +336,8 @@ monai/networks/nets/vnet.py,sha256=zaJi5kSiTLAuFHThSZfhJvHP6zKh3oBWsTWG-328O_g,1
 monai/networks/nets/voxelmorph.py,sha256=Q5VQFLLKSFqhsG0Z8_72ZGfK1nA4kdCfFnGbqI6Eofg,20665
 monai/networks/nets/vqvae.py,sha256=Zf9fTL_rluhuJhH6gTNB6iiKRfwBxfuuyhCdU9TLmAk,18417
 monai/networks/schedulers/__init__.py,sha256=rPmrNvnt8Bh9D2omPMgDiGVuT1XVJlgtlWIlqA_sjb4,755
-monai/networks/schedulers/ddim.py,sha256=a01QajgWksTYsPxs4DuBzy59mE_PcyTJedd6VqJv5g0,14376
-monai/networks/schedulers/ddpm.py,sha256=DkUwyI_TdorGtV9a33aJ8FrPU7CbpYOXYvgYP7uDxds,11318
+monai/networks/schedulers/ddim.py,sha256=MygHvgLB_NL9488DhHsE_g-EvV6DlDPtiBROpnCvDHc,14380
+monai/networks/schedulers/ddpm.py,sha256=LPqmlNJex32QrqcVb5s7XCNKVlFPsd_05-IJHpUJZPI,11387
 monai/networks/schedulers/pndm.py,sha256=9Qe8NOw_tvlpCBK7yvkmyriyGfIO5RRDV8ZKPh85cQY,14472
 monai/networks/schedulers/scheduler.py,sha256=X5eu5AmtNiads9cgaFy5r7BdlKYASSICyGSyF-fk6x8,9206
 monai/optimizers/__init__.py,sha256=XUL7o9vSL7bZImpxVZqcc1c8MwUMrOZL4nJ-mjAA7yM,796
@@ -379,7 +379,7 @@ monai/transforms/post/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJr4ZZJ
 monai/transforms/post/array.py,sha256=06Dfd_6cf-VJneet7WwbxFFlJEhYh365xu3fkcvGTws,45042
 monai/transforms/post/dictionary.py,sha256=pq4Oh3GoDcS6sjUkLvHzYmySxuxzVW7grjogFuRsUsA,43042
 monai/transforms/regularization/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJr4ZZJZLq0,573
-monai/transforms/regularization/array.py,sha256=yJbvs0-ElS7uK8jEZzYOL-nW2wizXvwni77s1pR7qvk,8036
+monai/transforms/regularization/array.py,sha256=oSG08b7opKGbHVZkpefdG1o0sX_F7-VoltzpNm5MB6k,8384
 monai/transforms/regularization/dictionary.py,sha256=b2hw8nElkQeyu3LZSnWvz7pQMcK9tCuNHpLueAGTQr8,4800
 monai/transforms/signal/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJr4ZZJZLq0,573
 monai/transforms/signal/array.py,sha256=eTlvqOIUQixh-voTNJcl532RvG4ZlQBNeHhg3TT3Cto,16325
@@ -416,8 +416,8 @@ monai/visualize/img2tensorboard.py,sha256=NnMcyfIFqX-jD7TBO3Rn02zt5uug79d_7pIIaV
 monai/visualize/occlusion_sensitivity.py,sha256=OQHEJLyIhB8zWqQsfKaX-1kvCjWFVYtLfS4dFC0nKFI,18160
 monai/visualize/utils.py,sha256=B-MhTVs7sQbIqYS3yPnpBwPw2K82rE2PBtGIfpwZtWM,9894
 monai/visualize/visualizer.py,sha256=qckyaMZCbezYUwE20k5yc-Pb7UozVavMDbrmyQwfYHY,1377
-monai_weekly-1.4.dev2440.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-monai_weekly-1.4.dev2440.dist-info/METADATA,sha256=_3k44c2ZfHiPSK9L-fDB3FhQP03fWtqUbjC-G1oa2q4,11172
-monai_weekly-1.4.dev2440.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-monai_weekly-1.4.dev2440.dist-info/top_level.txt,sha256=UaNwRzLGORdus41Ip446s3bBfViLkdkDsXDo34J2P44,6
-monai_weekly-1.4.dev2440.dist-info/RECORD,,
+monai_weekly-1.5.dev2442.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+monai_weekly-1.5.dev2442.dist-info/METADATA,sha256=ViLiKZdT67FCg3CtHo78A50SXdzyR7bPnOEcM_YSKeU,11187
+monai_weekly-1.5.dev2442.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
+monai_weekly-1.5.dev2442.dist-info/top_level.txt,sha256=UaNwRzLGORdus41Ip446s3bBfViLkdkDsXDo34J2P44,6
+monai_weekly-1.5.dev2442.dist-info/RECORD,,

{monai_weekly-1.4.dev2440.dist-info → monai_weekly-1.5.dev2442.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.1.0)
+Generator: setuptools (75.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any