monai-weekly 1.5.dev2450__py3-none-any.whl → 1.5.dev2452__py3-none-any.whl

monai/__init__.py

@@ -136,4 +136,4 @@ except BaseException:
 
     if MONAIEnvVars.debug():
         raise
-__commit_id__ = "21920a34bc00a114e430e1943e1fd1f572880919"
+__commit_id__ = "d36f0c80f716c5ad040f0f2cad11407e68d0f33a"

monai/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2024-12-15T02:32:50+0000",
+ "date": "2024-12-29T02:28:57+0000",
  "dirty": false,
  "error": null,
- "full-revisionid": "0726cee7ba6c1b31f34d54fc26fe6b8db5f5c79c",
- "version": "1.5.dev2450"
+ "full-revisionid": "889d81d09ea262ecaea1104224473012cab33a42",
+ "version": "1.5.dev2452"
 }
 '''  # END VERSION_JSON
 

monai/apps/utils.py

@@ -15,6 +15,7 @@ import hashlib
 import json
 import logging
 import os
+import re
 import shutil
 import sys
 import tarfile
@@ -30,7 +31,9 @@ from urllib.request import urlopen, urlretrieve
 from monai.config.type_definitions import PathLike
 from monai.utils import look_up_option, min_version, optional_import
 
+requests, has_requests = optional_import("requests")
 gdown, has_gdown = optional_import("gdown", "4.7.3")
+BeautifulSoup, has_bs4 = optional_import("bs4", name="BeautifulSoup")
 
 if TYPE_CHECKING:
     from tqdm import tqdm
@@ -298,6 +301,29 @@ def extractall(
     )
 
 
+def get_filename_from_url(data_url: str) -> str:
+    """
+    Get the filename from the URL link.
+    """
+    try:
+        response = requests.head(data_url, allow_redirects=True)
+        content_disposition = response.headers.get("Content-Disposition")
+        if content_disposition:
+            filename = re.findall('filename="?([^";]+)"?', content_disposition)
+            if filename:
+                return str(filename[0])
+        if "drive.google.com" in data_url:
+            response = requests.get(data_url)
+            if "text/html" in response.headers.get("Content-Type", ""):
+                soup = BeautifulSoup(response.text, "html.parser")
+                filename_div = soup.find("span", {"class": "uc-name-size"})
+                if filename_div:
+                    return str(filename_div.find("a").text)
+        return _basename(data_url)
+    except Exception as e:
+        raise Exception(f"Error processing URL: {e}") from e
+
+
 def download_and_extract(
     url: str,
     filepath: PathLike = "",
@@ -327,7 +353,18 @@ def download_and_extract(
             be False.
         progress: whether to display progress bar.
     """
+    url_filename_ext = "".join(Path(get_filename_from_url(url)).suffixes)
+    filepath_ext = "".join(Path(_basename(filepath)).suffixes)
+    if filepath not in ["", "."]:
+        if filepath_ext == "":
+            new_filepath = Path(filepath).with_suffix(url_filename_ext)
+            logger.warning(
+                f"filepath={filepath}, which missing file extension. Auto-appending extension to: {new_filepath}"
+            )
+            filepath = new_filepath
+    if filepath_ext and filepath_ext != url_filename_ext:
+        raise ValueError(f"File extension mismatch: expected extension {url_filename_ext}, but get {filepath_ext}")
     with tempfile.TemporaryDirectory() as tmp_dir:
-        filename = filepath or Path(tmp_dir, _basename(url)).resolve()
+        filename = filepath or Path(tmp_dir, get_filename_from_url(url)).resolve()
         download_url(url=url, filepath=filename, hash_val=hash_val, hash_type=hash_type, progress=progress)
         extractall(filepath=filename, output_dir=output_dir, file_type=file_type, has_base=has_base)

monai/data/image_reader.py

@@ -12,8 +12,11 @@
 from __future__ import annotations
 
 import glob
+import gzip
+import io
 import os
 import re
+import tempfile
 import warnings
 from abc import ABC, abstractmethod
 from collections.abc import Callable, Iterable, Iterator, Sequence
@@ -51,6 +54,9 @@ else:
     pydicom, has_pydicom = optional_import("pydicom")
     nrrd, has_nrrd = optional_import("nrrd", allow_namespace_pkg=True)
 
+cp, has_cp = optional_import("cupy")
+kvikio, has_kvikio = optional_import("kvikio")
+
 __all__ = ["ImageReader", "ITKReader", "NibabelReader", "NumpyReader", "PILReader", "PydicomReader", "NrrdReader"]
 
 
@@ -137,14 +143,18 @@ def _copy_compatible_dict(from_dict: dict, to_dict: dict):
             )
 
 
-def _stack_images(image_list: list, meta_dict: dict):
+def _stack_images(image_list: list, meta_dict: dict, to_cupy: bool = False):
     if len(image_list) <= 1:
         return image_list[0]
     if not is_no_channel(meta_dict.get(MetaKeys.ORIGINAL_CHANNEL_DIM, None)):
         channel_dim = int(meta_dict[MetaKeys.ORIGINAL_CHANNEL_DIM])
+        if to_cupy and has_cp:
+            return cp.concatenate(image_list, axis=channel_dim)
         return np.concatenate(image_list, axis=channel_dim)
     # stack at a new first dim as the channel dim, if `'original_channel_dim'` is unspecified
     meta_dict[MetaKeys.ORIGINAL_CHANNEL_DIM] = 0
+    if to_cupy and has_cp:
+        return cp.stack(image_list, axis=0)
     return np.stack(image_list, axis=0)
 
 
@@ -864,12 +874,18 @@ class NibabelReader(ImageReader):
     Load NIfTI format images based on Nibabel library.
 
     Args:
-        as_closest_canonical: if True, load the image as closest to canonical axis format.
-        squeeze_non_spatial_dims: if True, non-spatial singletons will be squeezed, e.g. (256,256,1,3) -> (256,256,3)
         channel_dim: the channel dimension of the input image, default is None.
             this is used to set original_channel_dim in the metadata, EnsureChannelFirstD reads this field.
             if None, `original_channel_dim` will be either `no_channel` or `-1`.
             most Nifti files are usually "channel last", no need to specify this argument for them.
+        as_closest_canonical: if True, load the image as closest to canonical axis format.
+        squeeze_non_spatial_dims: if True, non-spatial singletons will be squeezed, e.g. (256,256,1,3) -> (256,256,3)
+        to_gpu: If True, load the image into GPU memory using CuPy and Kvikio. This can accelerate data loading.
+            Default is False. CuPy and Kvikio are required for this option.
+            Note: For compressed NIfTI files, some operations may still be performed on CPU memory,
+            and the acceleration may not be significant. In some cases, it may be slower than loading on CPU.
+            In practical use, it's recommended to add a warm up call before the actual loading.
+            A related tutorial will be prepared in the future, and the document will be updated accordingly.
         kwargs: additional args for `nibabel.load` API. more details about available args:
             https://github.com/nipy/nibabel/blob/master/nibabel/loadsave.py
 
@@ -880,14 +896,42 @@ class NibabelReader(ImageReader):
         channel_dim: str | int | None = None,
         as_closest_canonical: bool = False,
         squeeze_non_spatial_dims: bool = False,
+        to_gpu: bool = False,
         **kwargs,
     ):
         super().__init__()
         self.channel_dim = float("nan") if channel_dim == "no_channel" else channel_dim
         self.as_closest_canonical = as_closest_canonical
         self.squeeze_non_spatial_dims = squeeze_non_spatial_dims
+        if to_gpu and (not has_cp or not has_kvikio):
+            warnings.warn(
+                "NibabelReader: CuPy and/or Kvikio not installed for GPU loading, falling back to CPU loading."
+            )
+            to_gpu = False
+
+        if to_gpu:
+            self.warmup_kvikio()
+
+        self.to_gpu = to_gpu
         self.kwargs = kwargs
 
+    def warmup_kvikio(self):
+        """
+        Warm up the Kvikio library to initialize the internal buffers, cuFile, GDS, etc.
+        This can accelerate the data loading process when `to_gpu` is set to True.
+        """
+        if has_cp and has_kvikio:
+            a = cp.arange(100)
+            with tempfile.NamedTemporaryFile() as tmp_file:
+                tmp_file_name = tmp_file.name
+                f = kvikio.CuFile(tmp_file_name, "w")
+                f.write(a)
+                f.close()
+
+                b = cp.empty_like(a)
+                f = kvikio.CuFile(tmp_file_name, "r")
+                f.read(b)
+
     def verify_suffix(self, filename: Sequence[PathLike] | PathLike) -> bool:
         """
         Verify whether the specified file or files format is supported by Nibabel reader.
@@ -916,6 +960,7 @@ class NibabelReader(ImageReader):
         img_: list[Nifti1Image] = []
 
         filenames: Sequence[PathLike] = ensure_tuple(data)
+        self.filenames = filenames
         kwargs_ = self.kwargs.copy()
         kwargs_.update(kwargs)
         for name in filenames:
@@ -936,10 +981,13 @@ class NibabelReader(ImageReader):
             img: a Nibabel image object loaded from an image file or a list of Nibabel image objects.
 
         """
+        # TODO: the actual type is list[np.ndarray | cp.ndarray]
+        # should figure out how to define correct types without having cupy not found error
+        # https://github.com/Project-MONAI/MONAI/pull/8188#discussion_r1886645918
         img_array: list[np.ndarray] = []
         compatible_meta: dict = {}
 
-        for i in ensure_tuple(img):
+        for i, filename in zip(ensure_tuple(img), self.filenames):
             header = self._get_meta_dict(i)
             header[MetaKeys.AFFINE] = self._get_affine(i)
             header[MetaKeys.ORIGINAL_AFFINE] = self._get_affine(i)
@@ -949,7 +997,7 @@ class NibabelReader(ImageReader):
                 header[MetaKeys.AFFINE] = self._get_affine(i)
             header[MetaKeys.SPATIAL_SHAPE] = self._get_spatial_shape(i)
             header[MetaKeys.SPACE] = SpaceKeys.RAS
-            data = self._get_array_data(i)
+            data = self._get_array_data(i, filename)
             if self.squeeze_non_spatial_dims:
                 for d in range(len(data.shape), len(header[MetaKeys.SPATIAL_SHAPE]), -1):
                     if data.shape[d - 1] == 1:
@@ -963,7 +1011,7 @@ class NibabelReader(ImageReader):
                 header[MetaKeys.ORIGINAL_CHANNEL_DIM] = self.channel_dim
             _copy_compatible_dict(header, compatible_meta)
 
-        return _stack_images(img_array, compatible_meta), compatible_meta
+        return _stack_images(img_array, compatible_meta, to_cupy=self.to_gpu), compatible_meta
 
     def _get_meta_dict(self, img) -> dict:
         """
@@ -1015,14 +1063,34 @@ class NibabelReader(ImageReader):
         spatial_rank = max(min(ndim, 3), 1)
         return np.asarray(size[:spatial_rank])
 
-    def _get_array_data(self, img):
+    def _get_array_data(self, img, filename):
         """
         Get the raw array data of the image, converted to Numpy array.
 
         Args:
             img: a Nibabel image object loaded from an image file.
-
-        """
+            filename: file name of the image.
+
+        """
+        if self.to_gpu:
+            file_size = os.path.getsize(filename)
+            image = cp.empty(file_size, dtype=cp.uint8)
+            with kvikio.CuFile(filename, "r") as f:
+                f.read(image)
+            if filename.endswith(".nii.gz"):
+                # for compressed data, have to tansfer to CPU to decompress
+                # and then transfer back to GPU. It is not efficient compared to .nii file
+                # and may be slower than CPU loading in some cases.
+                warnings.warn("Loading compressed NIfTI file into GPU may not be efficient.")
+                compressed_data = cp.asnumpy(image)
+                with gzip.GzipFile(fileobj=io.BytesIO(compressed_data)) as gz_file:
+                    decompressed_data = gz_file.read()
+
+                image = cp.frombuffer(decompressed_data, dtype=cp.uint8)
+            data_shape = img.shape
+            data_offset = img.dataobj.offset
+            data_dtype = img.dataobj.dtype
+            return image[data_offset:].view(data_dtype).reshape(data_shape, order="F")
         return np.asanyarray(img.dataobj, order="C")
 
 

monai/data/meta_tensor.py

@@ -553,7 +553,6 @@ class MetaTensor(MetaObj, torch.Tensor):
             However, if `get_track_meta()` is `False` or meta=None, a `torch.Tensor` is returned.
         """
         img = convert_to_tensor(im, track_meta=get_track_meta() and meta is not None)  # potentially ascontiguousarray
-
         # if not tracking metadata, return `torch.Tensor`
         if not isinstance(img, MetaTensor):
             return img

monai/engines/workflow.py

@@ -12,7 +12,7 @@
 from __future__ import annotations
 
 import warnings
-from collections.abc import Callable, Iterable, Sequence
+from collections.abc import Callable, Iterable, Sequence, Sized
 from typing import TYPE_CHECKING, Any
 
 import torch
@@ -121,24 +121,24 @@ class Workflow(Engine):
         to_kwargs: dict | None = None,
         amp_kwargs: dict | None = None,
     ) -> None:
-        if iteration_update is not None:
-            super().__init__(iteration_update)
-        else:
-            super().__init__(self._iteration)
+        super().__init__(self._iteration if iteration_update is None else iteration_update)
 
         if isinstance(data_loader, DataLoader):
-            sampler = data_loader.__dict__["sampler"]
+            sampler = getattr(data_loader, "sampler", None)
+
+            # set the epoch value for DistributedSampler objects when an epoch starts
             if isinstance(sampler, DistributedSampler):
 
                 @self.on(Events.EPOCH_STARTED)
                 def set_sampler_epoch(engine: Engine) -> None:
                     sampler.set_epoch(engine.state.epoch)
 
-            if epoch_length is None:
+        # if the epoch_length isn't given, attempt to get it from the length of the data loader
+        if epoch_length is None and isinstance(data_loader, Sized):
+            try:
                 epoch_length = len(data_loader)
-        else:
-            if epoch_length is None:
-                raise ValueError("If data_loader is not PyTorch DataLoader, must specify the epoch_length.")
+            except TypeError:  # raised when data_loader has an iterable dataset with no length, or is some other type
+                pass  # deliberately leave epoch_length as None
 
         # set all sharable data for the workflow based on Ignite engine.state
         self.state: Any = State(
@@ -147,7 +147,7 @@ class Workflow(Engine):
             iteration=0,
             epoch=0,
             max_epochs=max_epochs,
-            epoch_length=epoch_length,
+            epoch_length=epoch_length,  # None when the dataset is iterable and so has no length
             output=None,
             batch=None,
             metrics={},

monai/transforms/io/array.py

@@ -286,7 +286,6 @@ class LoadImage(Transform):
                 "    https://docs.monai.io/en/latest/installation.html#installing-the-recommended-dependencies.\n"
                 f"   The current registered: {self.readers}.\n{msg}"
             )
-
         img_array: NdarrayOrTensor
         img_array, meta_data = reader.get_data(img)
         img_array = convert_to_dst_type(img_array, dst=img_array, dtype=self.dtype)[0]

{monai_weekly-1.5.dev2450.dist-info → monai_weekly-1.5.dev2452.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: monai-weekly
-Version: 1.5.dev2450
+Version: 1.5.dev2452
 Summary: AI Toolkit for Healthcare Imaging
 Home-page: https://monai.io/
 Author: MONAI Consortium

{monai_weekly-1.5.dev2450.dist-info → monai_weekly-1.5.dev2452.dist-info}/RECORD

@@ -1,5 +1,5 @@
-monai/__init__.py,sha256=ppKjg4Vf78SuccS6v4N3gKSTfOuuv1dUTG_RwmR9rNc,4095
-monai/_version.py,sha256=4Qd2tQIN8lM0BAnUMqVz4dc4qTr9IVY34E1wWINAavo,503
+monai/__init__.py,sha256=p0xbEwBOl6_e0WPhyno_jg8uN7sKPY7HEvB1mYil_6g,4095
+monai/_version.py,sha256=6eSAlvPUvuAuoTXP1wXyqepsGxZ7CMLTdRL7oJqVIAw,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
@@ -10,7 +10,7 @@ monai/_extensions/gmm/gmm_cuda.cu,sha256=egWZBIpNYfOfxn0TKX82y-S2M6jg9NCzWwRcTLN
 monai/_extensions/gmm/gmm_cuda_linalg.cuh,sha256=Glqg2oAcUFUXg-DVfpROkiv-DdXvvVdM1nyiFm8qlHY,3520
 monai/apps/__init__.py,sha256=VDIc3HB_uFbqKL1TS-OeRvryEMDfzm22KJRzwpkXsGo,908
 monai/apps/datasets.py,sha256=msT58BoHlQFQpD4Tx-CThwAkkaUowoNZOgcH0THg0u0,35085
-monai/apps/utils.py,sha256=Gellkseuv3XKs-A6XcgbtqktQayv9NVIhX9tTQGM10I,14362
+monai/apps/utils.py,sha256=kJ200fyf_folGggBd2VK_CXjiDVMIAxaB6wxTj4NvBI,16099
 monai/apps/auto3dseg/__init__.py,sha256=DhUB2Ol0-iNAk1ZNmD1RkTODUOhdiibv8h9MgcLuF6s,1016
 monai/apps/auto3dseg/__main__.py,sha256=fCDhD8uhmJQKkKBxLO6hMJhEvZJRIsjTc1Ad3bYmNIY,1411
 monai/apps/auto3dseg/auto_runner.py,sha256=a4Ry93TkK0aTb68bwle8HoG4SzUbUf0IbDrY33jTReg,40106
@@ -131,12 +131,12 @@ monai/data/fft_utils.py,sha256=in9Zu8hC4oSVzuA-Zl236X6EkvgFka0RXdOxgvdGkv0,4448
 monai/data/folder_layout.py,sha256=IsHW1-Bkupn_T8r6MgFTIJQh5HwCg0xQwOKmgBtl0gE,6344
 monai/data/grid_dataset.py,sha256=O0gHf3BgrisH1erOMZNSpoIut92mydnNpzGYWnBKg4U,19483
 monai/data/image_dataset.py,sha256=OhNJ3awauWtqsDhefIGDw3UYGF3RoleeNUPdJOKg3kI,7008
-monai/data/image_reader.py,sha256=XDkYVWQN_eHoMI1iFFWN8ICI0x9AxKSc8bGSavHskfs,61776
+monai/data/image_reader.py,sha256=5Hd0rSkK7D-dWt6LENS2AJ8BZqkPLrlc0jdxRMOWGUM,65114
 monai/data/image_writer.py,sha256=rH6vboPFkX4ziN3lnrmK6AzAOQYI9tEiOJb7Al2tj-8,39856
 monai/data/iterable_dataset.py,sha256=A0L5jaxwnfgProBj96tlT160esI21yutnTf3a4c29Ms,13100
 monai/data/itk_torch_bridge.py,sha256=3th-B3tJuJE22JFfOUgGeTMOPh1czJEiSccFyn_Ob0w,14461
 monai/data/meta_obj.py,sha256=EDQdYbc4HkHcuDYbokvuIbDW-peqvnPW2JPWT8zgaNU,8827
-monai/data/meta_tensor.py,sha256=LCyAhyjZNh4ynFt2EPZFsKcledIXMDO-XFsx_VBom5I,27557
+monai/data/meta_tensor.py,sha256=iK3er8zkj88O4XxTOBO2slhuwxBKuM-3Xh_HUejxo2I,27556
 monai/data/samplers.py,sha256=LUCAHy38ddGm67oJJp3W6ITBsDRqyGCrKtYn-pjrWc4,5102
 monai/data/synthetic.py,sha256=H0MaQq2nnYxXEMlvOW1-XoWJWY_VKsgZ75tWLO1aCXg,7375
 monai/data/test_time_augmentation.py,sha256=KgIcPDwF_KelBCX118J5gx13sefGaDgQFUDgGWCZujA,9871
@@ -151,7 +151,7 @@ monai/engines/__init__.py,sha256=oV0zH5n8qPdCCNZCqLqN4Z7iqADouDtZmtswWQoZWOk,109
 monai/engines/evaluator.py,sha256=d0V4Ko1mcVsr9PtOhhtJYy4SVtrXuKdZ9yWM9mCYpAA,26961
 monai/engines/trainer.py,sha256=CmCw0C20A1EUgmpBt_eGHp9ObIJO5shqF7bQGJVskc0,38448
 monai/engines/utils.py,sha256=YGaa1Gk2b3bBtodbToGaSOD-s9X7wMgfgESOozZCLrM,15632
-monai/engines/workflow.py,sha256=S4DCLBSndcaM6LDb6xS-gTL8xCs8fiVejb-8O-pLKeQ,15226
+monai/engines/workflow.py,sha256=FXZt8wN8m2U7wmXwoI0t1ILeieqsHtPwt5P8cMX71_A,15495
 monai/fl/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJr4ZZJZLq0,573
 monai/fl/client/__init__.py,sha256=Wnkcf-Guhi-d29eAH0p51jz1Tn9WSVM4UUGbbb9SAqQ,725
 monai/fl/client/client_algo.py,sha256=vetQbSNmuvJRBEcu0AKM96gKYbkSXlu4HSriqK7wiiU,5098
@@ -370,7 +370,7 @@ monai/transforms/intensity/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJ
 monai/transforms/intensity/array.py,sha256=SpG3u9LPuQxDk77lEvPC4-tH1tiOtacDDfcyQydIhkI,121592
 monai/transforms/intensity/dictionary.py,sha256=MEeMKQckn6X-cEk51Z2YTGjt89RohBzFfO_jU3D06wk,85086
 monai/transforms/io/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJr4ZZJZLq0,573
-monai/transforms/io/array.py,sha256=z4aOxK44IhztN-LzG2uROYDwg_u1C6gcpx9ZH-ZhoVA,27482
+monai/transforms/io/array.py,sha256=QxB19z8aBhaSNlSkrubyoM0swHqTcDatWT0GrzmOOwM,27481
 monai/transforms/io/dictionary.py,sha256=64M9KUsKyzwXopDcarXT7JKIv9rHP8Ae-fYRvI0yBuM,18716
 monai/transforms/lazy/__init__.py,sha256=s9djSd6kvViPnFvMR11Dgd30Lv4oY6FaPJr4ZZJZLq0,573
 monai/transforms/lazy/array.py,sha256=2jNLmQ3_sMX7DdbfcT3Extpwe5FgOBbbz2RqlDlyNcw,1211
@@ -420,8 +420,8 @@ 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-1.5.dev2450.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-monai_weekly-1.5.dev2450.dist-info/METADATA,sha256=EADRhk1HSw2WCWT8O9ON63FfYXzmWTvz3Exd4B_FjNY,11876
-monai_weekly-1.5.dev2450.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-monai_weekly-1.5.dev2450.dist-info/top_level.txt,sha256=UaNwRzLGORdus41Ip446s3bBfViLkdkDsXDo34J2P44,6
-monai_weekly-1.5.dev2450.dist-info/RECORD,,
+monai_weekly-1.5.dev2452.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+monai_weekly-1.5.dev2452.dist-info/METADATA,sha256=Y5Mtm_9YodQyfPDM4guc4Z3Fsf5mI05D0LdtQRpnlSU,11876
+monai_weekly-1.5.dev2452.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+monai_weekly-1.5.dev2452.dist-info/top_level.txt,sha256=UaNwRzLGORdus41Ip446s3bBfViLkdkDsXDo34J2P44,6
+monai_weekly-1.5.dev2452.dist-info/RECORD,,