Merge branch 'dev' into fix/ignore-background-optional-y

Author: ericspod

docs/source/metrics.rst

@@ -158,6 +158,13 @@ Metrics
 
 `Fréchet Inception Distance`
 ------------------------------
+`Embedding Collapse`
+------------------------------
+.. autofunction:: compute_embedding_collapse
+
+.. autoclass:: EmbeddingCollapseMetric
+    :members:
+
 .. autofunction:: compute_frechet_distance
 
 .. autoclass:: FIDMetric

monai/apps/detection/utils/anchor_utils.py

@@ -253,7 +253,7 @@ def grid_anchors(self, grid_sizes: list[list[int]], strides: list[list[Tensor]])
             # compute anchor centers regarding to the image.
             # shifts_centers is [x_center, y_center] or [x_center, y_center, z_center]
             shifts_centers = [
-                torch.arange(0, size[axis], dtype=torch.int32, device=device) * stride[axis]
+                torch.arange(0, size[axis], dtype=torch.int32, device=device) * stride[axis] + stride[axis] // 2
                 for axis in range(self.spatial_dims)
             ]
 

monai/apps/nuclick/transforms.py

@@ -367,14 +367,14 @@ def inclusion_map(self, mask, dtype):
 
     def exclusion_map(self, others, dtype, jitter_range, drop_rate):
         point_mask = torch.zeros_like(others, dtype=dtype)
-        if np.random.choice([True, False], p=[drop_rate, 1 - drop_rate]):
+        if self.R.choice([True, False], p=[drop_rate, 1 - drop_rate]):
             return point_mask
 
         max_x = point_mask.shape[0] - 1
         max_y = point_mask.shape[1] - 1
         stats = measure.regionprops(convert_to_numpy(others))
         for stat in stats:
-            if np.random.choice([True, False], p=[drop_rate, 1 - drop_rate]):
+            if self.R.choice([True, False], p=[drop_rate, 1 - drop_rate]):
                 continue
 
             # random jitter

monai/auto3dseg/analyzer.py

@@ -216,50 +216,58 @@ def __init__(self, image_key: str, stats_name: str = DataStatsKeys.IMAGE_STATS)
         super().__init__(stats_name, report_format)
         self.update_ops(ImageStatsKeys.INTENSITY, SampleOperations())
 
+    @torch.no_grad()
     def __call__(self, data):
-        # Input Validation Addition
-        if not isinstance(data, dict):
-            raise TypeError(f"Input data must be a dict, but got {type(data).__name__}.")
-        if self.image_key not in data:
-            raise KeyError(f"Key '{self.image_key}' not found in input data.")
-        image = data[self.image_key]
-        if not isinstance(image, (np.ndarray, torch.Tensor, MetaTensor)):
-            raise TypeError(
-                f"Value for '{self.image_key}' must be a numpy array, torch.Tensor, or MetaTensor, "
-                f"but got {type(image).__name__}."
-            )
-        if image.ndim < 3:
-            raise ValueError(
-                f"Image data under '{self.image_key}' must have at least 3 dimensions, but got shape {image.shape}."
-            )
-            # --- End of validation ---
         """
-        Callable to execute the pre-defined functions
+        Callable to execute the pre-defined functions.
 
         Returns:
             A dictionary. The dict has the key in self.report_format. The value of
             ImageStatsKeys.INTENSITY is in a list format. Each element of the value list
             has stats pre-defined by SampleOperations (max, min, ....).
 
         Raises:
-            RuntimeError if the stats report generated is not consistent with the pre-
+            KeyError: if ``self.image_key`` is not present in the input data.
+            TypeError: if the input data is not a dictionary, or if the image value is
+                not a numpy array, torch.Tensor, or MetaTensor.
+            ValueError: if the image has fewer than 3 dimensions, or if pre-computed
+                ``nda_croppeds`` is not a list/tuple with one entry per image channel.
+            RuntimeError: if the stats report generated is not consistent with the pre-
                 defined report_format.
 
         Note:
             The stats operation uses numpy and torch to compute max, min, and other
             functions. If the input has nan/inf, the stats results will be nan/inf.
 
         """
+        if not isinstance(data, dict):
+            raise TypeError(f"Input data must be a dict, but got {type(data).__name__}.")
+        if self.image_key not in data:
+            raise KeyError(f"Key '{self.image_key}' not found in input data.")
+        image = data[self.image_key]
+        if not isinstance(image, (np.ndarray, torch.Tensor, MetaTensor)):
+            raise TypeError(
+                f"Value for '{self.image_key}' must be a numpy array, torch.Tensor, or MetaTensor, "
+                f"but got {type(image).__name__}."
+            )
+        if image.ndim < 3:
+            raise ValueError(
+                f"Image data under '{self.image_key}' must have at least 3 dimensions, but got shape {image.shape}."
+            )
+
         d = dict(data)
         start = time.time()
-        restore_grad_state = torch.is_grad_enabled()
-        torch.set_grad_enabled(False)
-
         ndas = [d[self.image_key][i] for i in range(d[self.image_key].shape[0])]
-        if "nda_croppeds" not in d:
+        if "nda_croppeds" in d:
+            nda_croppeds = d["nda_croppeds"]
+            if not isinstance(nda_croppeds, (list, tuple)) or len(nda_croppeds) != len(ndas):
+                raise ValueError(
+                    "Pre-computed 'nda_croppeds' must be a list or tuple with one entry per image channel "
+                    f"(expected {len(ndas)})."
+                )
+        else:
             nda_croppeds = [get_foreground_image(nda) for nda in ndas]
 
-        # perform calculation
         report = deepcopy(self.get_report_format())
 
         report[ImageStatsKeys.SHAPE] = [list(nda.shape) for nda in ndas]
@@ -284,7 +292,6 @@ def __call__(self, data):
 
         d[self.stats_name] = report
 
-        torch.set_grad_enabled(restore_grad_state)
         logger.debug(f"Get image stats spent {time.time() - start}")
         return d
 
@@ -321,6 +328,7 @@ def __init__(self, image_key: str, label_key: str, stats_name: str = DataStatsKe
         super().__init__(stats_name, report_format)
         self.update_ops(ImageStatsKeys.INTENSITY, SampleOperations())
 
+    @torch.no_grad()
     def __call__(self, data: Mapping) -> dict:
         """
         Callable to execute the pre-defined functions
@@ -341,9 +349,6 @@ def __call__(self, data: Mapping) -> dict:
 
         d = dict(data)
         start = time.time()
-        restore_grad_state = torch.is_grad_enabled()
-        torch.set_grad_enabled(False)
-
         ndas = [d[self.image_key][i] for i in range(d[self.image_key].shape[0])]
         ndas_label = d[self.label_key]  # (H,W,D)
 
@@ -353,7 +358,6 @@ def __call__(self, data: Mapping) -> dict:
         nda_foregrounds = [get_foreground_label(nda, ndas_label) for nda in ndas]
         nda_foregrounds = [nda if nda.numel() > 0 else MetaTensor([0.0]) for nda in nda_foregrounds]
 
-        # perform calculation
         report = deepcopy(self.get_report_format())
 
         report[ImageStatsKeys.INTENSITY] = [
@@ -365,7 +369,6 @@ def __call__(self, data: Mapping) -> dict:
 
         d[self.stats_name] = report
 
-        torch.set_grad_enabled(restore_grad_state)
         logger.debug(f"Get foreground image stats spent {time.time() - start}")
         return d
 
@@ -418,6 +421,7 @@ def __init__(
         id_seq = ID_SEP_KEY.join([LabelStatsKeys.LABEL, "0", LabelStatsKeys.IMAGE_INTST])
         self.update_ops_nested_label(id_seq, SampleOperations())
 
+    @torch.no_grad()
     def __call__(self, data: Mapping[Hashable, MetaTensor]) -> dict[Hashable, MetaTensor | dict]:
         """
         Callable to execute the pre-defined functions.
@@ -470,19 +474,15 @@ def __call__(self, data: Mapping[Hashable, MetaTensor]) -> dict[Hashable, MetaTe
         start = time.time()
         image_tensor = d[self.image_key]
         label_tensor = d[self.label_key]
-        # Check if either tensor is on CUDA to determine if we should move both to CUDA for processing
         using_cuda = any(
             isinstance(t, (torch.Tensor, MetaTensor)) and t.device.type == "cuda" for t in (image_tensor, label_tensor)
         )
-        restore_grad_state = torch.is_grad_enabled()
-        torch.set_grad_enabled(False)
 
         if isinstance(image_tensor, (MetaTensor, torch.Tensor)) and isinstance(
             label_tensor, (MetaTensor, torch.Tensor)
         ):
             if label_tensor.device != image_tensor.device:
                 if using_cuda:
-                    # Move both tensors to CUDA when mixing devices
                     cuda_device = image_tensor.device if image_tensor.device.type == "cuda" else label_tensor.device
                     image_tensor = cast(MetaTensor, image_tensor.to(cuda_device))
                     label_tensor = cast(MetaTensor, label_tensor.to(cuda_device))
@@ -548,7 +548,6 @@ def __call__(self, data: Mapping[Hashable, MetaTensor]) -> dict[Hashable, MetaTe
 
         d[self.stats_name] = report  # type: ignore[assignment]
 
-        torch.set_grad_enabled(restore_grad_state)
         logger.debug(f"Get label stats spent {time.time() - start}")
         return d  # type: ignore[return-value]
 

monai/losses/spectral_loss.py

@@ -55,8 +55,8 @@ def __init__(
         self.fft_norm = fft_norm
 
     def forward(self, input: torch.Tensor, target: torch.Tensor) -> torch.Tensor:
-        input_amplitude = self._get_fft_amplitude(target)
-        target_amplitude = self._get_fft_amplitude(input)
+        input_amplitude = self._get_fft_amplitude(input)
+        target_amplitude = self._get_fft_amplitude(target)
 
         # Compute distance between amplitude of frequency components
         # See Section 3.3 from https://arxiv.org/abs/2005.00341

monai/losses/ssim_loss.py

@@ -111,17 +111,17 @@ def forward(self, input: torch.Tensor, target: torch.Tensor) -> torch.Tensor:
                 # 2D data
                 x = torch.ones([1,1,10,10])/2
                 y = torch.ones([1,1,10,10])/2
-                print(1-SSIMLoss(spatial_dims=2)(x,y))
+                print(SSIMLoss(spatial_dims=2)(x,y))
 
                 # pseudo-3D data
                 x = torch.ones([1,5,10,10])/2  # 5 could represent number of slices
                 y = torch.ones([1,5,10,10])/2
-                print(1-SSIMLoss(spatial_dims=2)(x,y))
+                print(SSIMLoss(spatial_dims=2)(x,y))
 
                 # 3D data
                 x = torch.ones([1,1,10,10,10])/2
                 y = torch.ones([1,1,10,10,10])/2
-                print(1-SSIMLoss(spatial_dims=3)(x,y))
+                print(SSIMLoss(spatial_dims=3)(x,y))
         """
         ssim_value = self.ssim_metric._compute_tensor(input, target).view(-1, 1)
         loss: torch.Tensor = 1 - ssim_value

monai/metrics/__init__.py

@@ -16,6 +16,7 @@
 from .calibration import CalibrationErrorMetric, CalibrationReduction, calibration_binning
 from .confusion_matrix import ConfusionMatrixMetric, compute_confusion_matrix_metric, get_confusion_matrix
 from .cumulative_average import CumulativeAverage
+from .embedding_collapse import EmbeddingCollapseMetric, compute_embedding_collapse
 from .f_beta_score import FBetaScore
 from .fid import FIDMetric, compute_frechet_distance
 from .froc import compute_fp_tp_probs, compute_fp_tp_probs_nd, compute_froc_curve_data, compute_froc_score