Merge branch 'dev' into bug/lps_orientation_transform

Author: KumoLiu

monai/apps/auto3dseg/auto_runner.py

@@ -194,6 +194,15 @@ class AutoRunner:
             ├── segresnet2d_0       # network scripts/configs/checkpoints and pickle object of the algo
             └── swinunetr_0         # network scripts/configs/checkpoints and pickle object of the algo
 
+
+        The input config requires at least the following keys:
+            - ``modality``: the modality of the data, e.g. "ct", "mri", etc.
+            - ``datalist``: the path to the datalist file in JSON format.
+            - ``dataroot``: the root directory of the data files.
+
+        For the datalist file format, see the description under :py:func:`monai.data.load_decathlon_datalist`.
+        Note that the AutoRunner will use the "validation" key in the datalist file if it exists, otherwise
+        it will do cross-validation, by default with five folds (this is hardcoded).
     """
 
     analyze_params: dict | None

monai/data/decathlon_datalist.py

@@ -92,8 +92,42 @@ def load_decathlon_datalist(
 ) -> list[dict]:
     """Load image/label paths of decathlon challenge from JSON file
 
-    Json file is similar to what you get from http://medicaldecathlon.com/
-    Those dataset.json files
+    JSON file should follow the format of the Medical Segmentation Decathlon
+    datalist.json files, see http://medicaldecathlon.com.
+    The files are structured as follows:
+
+    .. code-block:: python
+
+        {
+            "metadata_key_0": "metadata_value_0",
+            "metadata_key_1": "metadata_value_1",
+            ...,
+            "training": [
+                {"image": "path/to/image_1.nii.gz", "label": "path/to/label_1.nii.gz"},
+                {"image": "path/to/image_2.nii.gz", "label": "path/to/label_2.nii.gz"},
+                ...
+            ],
+            "test": [
+                "path/to/image_3.nii.gz",
+                "path/to/image_4.nii.gz",
+                ...
+            ]
+        }
+
+
+    The metadata keys are optional for loading the datalist, but include:
+        - some string items: ``name``, ``description``, ``reference``, ``licence``, ``release``, ``tensorImageSize``
+        - two dict items: ``modality`` (keyed by channel index), and ``labels`` (keyed by label index)
+        - and two integer items: ``numTraining`` and ``numTest``, with the number of items.
+
+    The ``training`` key contains a list of dictionaries, each of which has at least
+    the ``image`` and ``label`` keys.
+    The image and label are loaded by :py:func:`monai.transforms.LoadImaged`, so both can be either
+    a single file path or a list of file paths, in which case they are loaded as multi-channel images.
+    Each item can also include a ``fold`` key for cross-validation purposes.
+    The "test" key contains a list of image paths, without labels, MONAI also supports a "validation" list
+    with the same format as the "training" list.
+
 
     Args:
         data_list_file_path: the path to the json file of datalist.
@@ -107,11 +141,11 @@ def load_decathlon_datalist(
 
     Returns a list of data items, each of which is a dict keyed by element names, for example:
 
-    .. code-block::
+    .. code-block:: python
 
         [
-            {'image': '/workspace/data/chest_19.nii.gz',  'label': 0},
-            {'image': '/workspace/data/chest_31.nii.gz',  'label': 1}
+            {'image': '/workspace/data/chest_19.nii.gz',  'label': '/workspace/labels/chest_19.nii.gz'},
+            {'image': '/workspace/data/chest_31.nii.gz',  'label': '/workspace/labels/chest_31.nii.gz'},
         ]
 
     """
@@ -134,7 +168,8 @@ def load_decathlon_datalist(
 
 
 def load_decathlon_properties(data_property_file_path: PathLike, property_keys: Sequence[str] | str) -> dict:
-    """Load the properties from the JSON file contains data property with specified `property_keys`.
+    """Extract the properties with the specified keys from the Decathlon JSON file.
+    See under `load_decathlon_datalist` for the expected keys in the Decathlon challenge.
 
     Args:
         data_property_file_path: the path to the JSON file of data properties.

monai/transforms/intensity/dictionary.py

@@ -1836,7 +1836,7 @@ class HistogramNormalized(MapTransform):
             See also: :py:class:`monai.transforms.compose.MapTransform`
         num_bins: number of the bins to use in histogram, default to `256`. for more details:
             https://numpy.org/doc/stable/reference/generated/numpy.histogram.html.
-        min: the min value to normalize input image, default to `255`.
+        min: the min value to normalize input image, default to `0`.
         max: the max value to normalize input image, default to `255`.
         mask: if provided, must be ndarray of bools or 0s and 1s, and same shape as `image`.
             only points at which `mask==True` are used for the equalization.

tests/__init__.py

@@ -8,32 +8,3 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
-from __future__ import annotations
-
-import sys
-import unittest
-import warnings
-
-
-def _enter_pr_4800(self):
-    """
-    code from https://github.com/python/cpython/pull/4800
-    """
-    # The __warningregistry__'s need to be in a pristine state for tests
-    # to work properly.
-    for v in list(sys.modules.values()):
-        if getattr(v, "__warningregistry__", None):
-            v.__warningregistry__ = {}
-    self.warnings_manager = warnings.catch_warnings(record=True)
-    self.warnings = self.warnings_manager.__enter__()
-    warnings.simplefilter("always", self.expected)
-    return self
-
-
-# FIXME: workaround for https://bugs.python.org/issue29620
-try:
-    # Suppression for issue #494:  tests/__init__.py:34: error: Cannot assign to a method
-    unittest.case._AssertWarnsContext.__enter__ = _enter_pr_4800  # type: ignore
-except AttributeError:
-    pass

tests/apps/detection/networks/test_retinanet.py

@@ -20,7 +20,7 @@
 from monai.networks import eval_mode
 from monai.networks.nets import resnet10, resnet18, resnet34, resnet50, resnet101, resnet152, resnet200
 from monai.utils import ensure_tuple, optional_import
-from tests.test_utils import SkipIfBeforePyTorchVersion, dict_product, skip_if_quick, test_onnx_save, test_script_save
+from tests.test_utils import dict_product, skip_if_quick, test_onnx_save, test_script_save
 
 _, has_torchvision = optional_import("torchvision")
 
@@ -94,7 +94,6 @@
 TEST_CASES_TS = [[params["model"], *params["case"]] for params in dict_product(model=MODEL_LIST, case=[TEST_CASE_1])]
 
 
-@SkipIfBeforePyTorchVersion((1, 12))
 @unittest.skipUnless(has_torchvision, "Requires torchvision")
 @skip_if_quick
 class TestRetinaNet(unittest.TestCase):

tests/apps/detection/networks/test_retinanet_detector.py

@@ -21,7 +21,7 @@
 from monai.apps.detection.utils.anchor_utils import AnchorGeneratorWithAnchorShape
 from monai.networks import eval_mode, train_mode
 from monai.utils import optional_import
-from tests.test_utils import SkipIfBeforePyTorchVersion, skip_if_quick, test_script_save
+from tests.test_utils import skip_if_quick, test_script_save
 
 _, has_torchvision = optional_import("torchvision")
 
@@ -110,7 +110,6 @@ def forward(self, images):
         return {self.cls_key: [torch.randn(out_cls_shape)], self.box_reg_key: [torch.randn(out_box_reg_shape)]}
 
 
-@SkipIfBeforePyTorchVersion((1, 11))
 @unittest.skipUnless(has_torchvision, "Requires torchvision")
 @skip_if_quick
 class TestRetinaNetDetector(unittest.TestCase):

tests/apps/detection/utils/test_anchor_box.py

@@ -18,7 +18,7 @@
 
 from monai.apps.detection.utils.anchor_utils import AnchorGenerator, AnchorGeneratorWithAnchorShape
 from monai.utils import optional_import
-from tests.test_utils import SkipIfBeforePyTorchVersion, assert_allclose, test_script_save
+from tests.test_utils import assert_allclose, test_script_save
 
 _, has_torchvision = optional_import("torchvision")
 
@@ -39,7 +39,6 @@
 ]
 
 
-@SkipIfBeforePyTorchVersion((1, 11))
 @unittest.skipUnless(has_torchvision, "Requires torchvision")
 class TestAnchorGenerator(unittest.TestCase):
     @parameterized.expand(TEST_CASES_2D)

tests/apps/maisi/networks/test_autoencoderkl_maisi.py

@@ -19,7 +19,6 @@
 from monai.apps.generation.maisi.networks.autoencoderkl_maisi import AutoencoderKlMaisi
 from monai.networks import eval_mode
 from monai.utils import optional_import
-from tests.test_utils import SkipIfBeforePyTorchVersion
 
 tqdm, has_tqdm = optional_import("tqdm", name="tqdm")
 _, has_einops = optional_import("einops")
@@ -87,7 +86,6 @@ def test_shape(self, input_param, input_shape, expected_shape, expected_latent_s
             self.assertEqual(result[2].shape, expected_latent_shape)
 
     @parameterized.expand(CASES)
-    @SkipIfBeforePyTorchVersion((1, 11))
     def test_shape_with_convtranspose_and_checkpointing(
         self, input_param, input_shape, expected_shape, expected_latent_shape
     ):
@@ -152,7 +150,6 @@ def test_shape_reconstruction(self):
             result = net.reconstruct(torch.randn(input_shape).to(device))
             self.assertEqual(result.shape, expected_shape)
 
-    @SkipIfBeforePyTorchVersion((1, 11))
     def test_shape_reconstruction_with_convtranspose_and_checkpointing(self):
         input_param, input_shape, expected_shape, _ = CASES[0]
         input_param = input_param.copy()
@@ -170,7 +167,6 @@ def test_shape_encode(self):
             self.assertEqual(result[0].shape, expected_latent_shape)
             self.assertEqual(result[1].shape, expected_latent_shape)
 
-    @SkipIfBeforePyTorchVersion((1, 11))
     def test_shape_encode_with_convtranspose_and_checkpointing(self):
         input_param, input_shape, _, expected_latent_shape = CASES[0]
         input_param = input_param.copy()
@@ -190,7 +186,6 @@ def test_shape_sampling(self):
             )
             self.assertEqual(result.shape, expected_latent_shape)
 
-    @SkipIfBeforePyTorchVersion((1, 11))
     def test_shape_sampling_convtranspose_and_checkpointing(self):
         input_param, _, _, expected_latent_shape = CASES[0]
         input_param = input_param.copy()
@@ -209,7 +204,6 @@ def test_shape_decode(self):
             result = net.decode(torch.randn(latent_shape).to(device))
             self.assertEqual(result.shape, expected_input_shape)
 
-    @SkipIfBeforePyTorchVersion((1, 11))
     def test_shape_decode_convtranspose_and_checkpointing(self):
         input_param, expected_input_shape, _, latent_shape = CASES[0]
         input_param = input_param.copy()

tests/apps/maisi/networks/test_controlnet_maisi.py

@@ -20,7 +20,6 @@
 from monai.apps.generation.maisi.networks.controlnet_maisi import ControlNetMaisi
 from monai.networks import eval_mode
 from monai.utils import optional_import
-from tests.test_utils import SkipIfBeforePyTorchVersion
 
 _, has_einops = optional_import("einops")
 
@@ -127,7 +126,6 @@
 ]
 
 
-@SkipIfBeforePyTorchVersion((2, 0))
 class TestControlNet(unittest.TestCase):
     @parameterized.expand(TEST_CASES)
     @skipUnless(has_einops, "Requires einops")