fix ci and format

Signed-off-by: YunLiu <55491388+KumoLiu@users.noreply.github.com>

Author: KumoLiu

monai/bundle/scripts.py

@@ -647,6 +647,7 @@ def load(
     workflow_name: str | BundleWorkflow | None = None,
     args_file: str | None = None,
     copy_model_args: dict | None = None,
+    net_override: dict | None = None,
 ) -> object | tuple[torch.nn.Module, dict, dict] | Any:
     """
     Load model weights or TorchScript module of a bundle.
@@ -692,7 +693,7 @@ def load(
         workflow_name: specified bundle workflow name, should be a string or class, default to "ConfigWorkflow".
         args_file: a JSON or YAML file to provide default values for all the args in "download" function.
         copy_model_args: other arguments for the `monai.networks.copy_model_state` function.
-        net_kwargs: other arguments that are used to instantiate the network class defined by `net_name`.
+        net_override: id-value pairs to override the parameters in the network of the bundle, default to `None`.
 
     Returns:
         1. If `load_ts_module` is `False` and `model` is `None`,

monai/networks/nets/swin_unetr.py

@@ -101,13 +101,13 @@ def __init__(
         Examples::
 
             # for 3D single channel input with size (96,96,96), 4-channel output and feature size of 48.
-            >>> net = SwinUNETR(img_size=(96,96,96), in_channels=1, out_channels=4, feature_size=48)
+            >>> net = SwinUNETR(in_channels=1, out_channels=4, feature_size=48)
 
             # for 3D 4-channel input with size (128,128,128), 3-channel output and (2,4,2,2) layers in each stage.
-            >>> net = SwinUNETR(img_size=(128,128,128), in_channels=4, out_channels=3, depths=(2,4,2,2))
+            >>> net = SwinUNETR(in_channels=4, out_channels=3, depths=(2,4,2,2))
 
             # for 2D single channel input with size (96,96), 2-channel output and gradient checkpointing.
-            >>> net = SwinUNETR(img_size=(96,96), in_channels=3, out_channels=2, use_checkpoint=True, spatial_dims=2)
+            >>> net = SwinUNETR(in_channels=3, out_channels=2, use_checkpoint=True, spatial_dims=2)
 
         """
 
@@ -118,12 +118,9 @@ def __init__(
 
         self.patch_size = patch_size
 
-        img_size = ensure_tuple_rep(img_size, spatial_dims)
         patch_sizes = ensure_tuple_rep(self.patch_size, spatial_dims)
         window_size = ensure_tuple_rep(window_size, spatial_dims)
 
-        self._check_input_size(img_size)
-
         if not (0 <= drop_rate <= 1):
             raise ValueError("dropout rate should be between 0 and 1.")
 
@@ -1097,7 +1094,7 @@ def filter_swinunetr(key, value):
         from monai.networks.utils import copy_model_state
         from monai.networks.nets.swin_unetr import SwinUNETR, filter_swinunetr
 
-        model = SwinUNETR(img_size=(96, 96, 96), in_channels=1, out_channels=3, feature_size=48)
+        model = SwinUNETR(in_channels=1, out_channels=3, feature_size=48)
         resource = (
             "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/ssl_pretrained_weights.pth"
         )

monai/utils/jupyter_utils.py

@@ -234,7 +234,7 @@ def plot_engine_status(
 
 
 def _get_loss_from_output(
-    output: list[torch.Tensor | dict[str, torch.Tensor]] | dict[str, torch.Tensor] | torch.Tensor,
+    output: list[torch.Tensor | dict[str, torch.Tensor]] | dict[str, torch.Tensor] | torch.Tensor
 ) -> torch.Tensor:
     """Returns a single value from the network output, which is a dict or tensor."""
 

tests/networks/nets/test_swin_unetr.py

@@ -51,7 +51,6 @@
                                         "spatial_dims": len(img_size),
                                         "in_channels": in_channels,
                                         "out_channels": out_channels,
-                                        "img_size": img_size,
                                         "feature_size": feature_size,
                                         "depths": depth,
                                         "norm_name": norm_name,
@@ -67,7 +66,7 @@
 
 TEST_CASE_FILTER = [
     [
-        {"img_size": (96, 96, 96), "in_channels": 1, "out_channels": 14, "feature_size": 48, "use_checkpoint": True},
+        {"in_channels": 1, "out_channels": 14, "feature_size": 48, "use_checkpoint": True},
         "swinViT.layers1.0.blocks.0.norm1.weight",
         torch.tensor([0.9473, 0.9343, 0.8566, 0.8487, 0.8065, 0.7779, 0.6333, 0.5555]),
     ]
@@ -85,30 +84,13 @@ def test_shape(self, input_param, input_shape, expected_shape):
 
     def test_ill_arg(self):
         with self.assertRaises(ValueError):
-            SwinUNETR(
-                in_channels=1,
-                out_channels=3,
-                img_size=(128, 128, 128),
-                feature_size=24,
-                norm_name="instance",
-                attn_drop_rate=4,
-            )
+            SwinUNETR(spatial_dims=1, in_channels=1, out_channels=2, feature_size=48, norm_name="instance")
 
         with self.assertRaises(ValueError):
-            SwinUNETR(in_channels=1, out_channels=2, img_size=(96, 96), feature_size=48, norm_name="instance")
+            SwinUNETR(in_channels=1, out_channels=4, feature_size=50, norm_name="instance")
 
         with self.assertRaises(ValueError):
-            SwinUNETR(in_channels=1, out_channels=4, img_size=(96, 96, 96), feature_size=50, norm_name="instance")
-
-        with self.assertRaises(ValueError):
-            SwinUNETR(
-                in_channels=1,
-                out_channels=3,
-                img_size=(85, 85, 85),
-                feature_size=24,
-                norm_name="instance",
-                drop_rate=0.4,
-            )
+            SwinUNETR(in_channels=1, out_channels=3, feature_size=24, norm_name="instance", drop_rate=-1)
 
     def test_patch_merging(self):
         dim = 10