kaiko-eva 0.0.1__py3-none-any.whl → 0.0.2__py3-none-any.whl

eva/vision/data/datasets/segmentation/total_segmentator.py

@@ -6,25 +6,26 @@ from glob import glob
 from typing import Callable, Dict, List, Literal, Tuple
 
 import numpy as np
+from torchvision import tv_tensors
 from torchvision.datasets import utils
 from typing_extensions import override
 
 from eva.vision.data.datasets import _utils, _validators, structs
 from eva.vision.data.datasets.segmentation import base
-from eva.vision.utils import io
+from eva.vision.utils import convert, io
 
 
 class TotalSegmentator2D(base.ImageSegmentation):
     """TotalSegmentator 2D segmentation dataset."""
 
-    _train_index_ranges: List[Tuple[int, int]] = [(0, 83)]
-    """Train range indices."""
+    _expected_dataset_lengths: Dict[str, int] = {
+        "train_small": 29892,
+        "val_small": 6480,
+    }
+    """Dataset version and split to the expected size."""
 
-    _val_index_ranges: List[Tuple[int, int]] = [(83, 103)]
-    """Validation range indices."""
-
-    _n_slices_per_image: int = 20
-    """The amount of slices to sample per 3D CT scan image."""
+    _sample_every_n_slices: int | None = None
+    """The amount of slices to sub-sample per 3D CT scan image."""
 
     _resources_full: List[structs.DownloadResource] = [
         structs.DownloadResource(
@@ -48,11 +49,10 @@ class TotalSegmentator2D(base.ImageSegmentation):
         self,
         root: str,
         split: Literal["train", "val"] | None,
-        version: Literal["small", "full"] = "small",
+        version: Literal["small", "full"] | None = "small",
         download: bool = False,
-        image_transforms: Callable | None = None,
-        target_transforms: Callable | None = None,
-        image_target_transforms: Callable | None = None,
+        as_uint8: bool = True,
+        transforms: Callable | None = None,
     ) -> None:
         """Initialize dataset.
 
@@ -60,33 +60,26 @@ class TotalSegmentator2D(base.ImageSegmentation):
             root: Path to the root directory of the dataset. The dataset will
                 be downloaded and extracted here, if it does not already exist.
             split: Dataset split to use. If `None`, the entire dataset is used.
-            version: The version of the dataset to initialize.
+            version: The version of the dataset to initialize. If `None`, it will
+                use the files located at root as is and wont perform any checks.
             download: Whether to download the data for the specified split.
                 Note that the download will be executed only by additionally
                 calling the :meth:`prepare_data` method and if the data does not
                 exist yet on disk.
-            image_transforms: A function/transform that takes in an image
-                and returns a transformed version.
-            target_transforms: A function/transform that takes in the target
-                and transforms it.
-            image_target_transforms: A function/transforms that takes in an
-                image and a label and returns the transformed versions of both.
-                This transform happens after the `image_transforms` and
-                `target_transforms`.
+            as_uint8: Whether to convert and return the images as a 8-bit.
+            transforms: A function/transforms that takes in an image and a target
+                mask and returns the transformed versions of both.
         """
-        super().__init__(
-            image_transforms=image_transforms,
-            target_transforms=target_transforms,
-            image_target_transforms=image_target_transforms,
-        )
+        super().__init__(transforms=transforms)
 
         self._root = root
         self._split = split
         self._version = version
         self._download = download
+        self._as_uint8 = as_uint8
 
         self._samples_dirs: List[str] = []
-        self._indices: List[int] = []
+        self._indices: List[Tuple[int, int]] = []
 
     @functools.cached_property
     @override
@@ -107,7 +100,8 @@ class TotalSegmentator2D(base.ImageSegmentation):
 
     @override
     def filename(self, index: int) -> str:
-        sample_dir = self._samples_dirs[self._indices[index]]
+        sample_idx, _ = self._indices[index]
+        sample_dir = self._samples_dirs[sample_idx]
         return os.path.join(sample_dir, "ct.nii.gz")
 
     @override
@@ -122,53 +116,58 @@ class TotalSegmentator2D(base.ImageSegmentation):
 
     @override
     def validate(self) -> None:
+        if self._version is None:
+            return
+
         _validators.check_dataset_integrity(
             self,
-            length=1660 if self._split == "train" else 400,
+            length=self._expected_dataset_lengths.get(f"{self._split}_{self._version}", 0),
             n_classes=117,
             first_and_last_labels=("adrenal_gland_left", "vertebrae_T9"),
         )
 
     @override
     def __len__(self) -> int:
-        return len(self._indices) * self._n_slices_per_image
+        return len(self._indices)
 
     @override
-    def load_image(self, index: int) -> np.ndarray:
-        image_path = self._get_image_path(index)
-        slice_index = self._get_sample_slice_index(index)
+    def load_image(self, index: int) -> tv_tensors.Image:
+        sample_index, slice_index = self._indices[index]
+        image_path = self._get_image_path(sample_index)
         image_array = io.read_nifti_slice(image_path, slice_index)
-        return image_array.repeat(3, axis=2)
+        if self._as_uint8:
+            image_array = convert.to_8bit(image_array)
+        image_rgb_array = image_array.repeat(3, axis=2)
+        return tv_tensors.Image(image_rgb_array.transpose(2, 0, 1))
 
     @override
-    def load_mask(self, index: int) -> np.ndarray:
-        masks_dir = self._get_masks_dir(index)
-        slice_index = self._get_sample_slice_index(index)
+    def load_mask(self, index: int) -> tv_tensors.Mask:
+        sample_index, slice_index = self._indices[index]
+        masks_dir = self._get_masks_dir(sample_index)
         mask_paths = (os.path.join(masks_dir, label + ".nii.gz") for label in self.classes)
-        masks = [io.read_nifti_slice(path, slice_index) for path in mask_paths]
-        return np.concatenate(masks, axis=-1)
-
-    def _get_masks_dir(self, index: int) -> str:
-        """Returns the directory of the corresponding masks."""
-        sample_dir = self._get_sample_dir(index)
-        return os.path.join(self._root, sample_dir, "segmentations")
+        one_hot_encoded = np.concatenate(
+            [io.read_nifti_slice(path, slice_index) for path in mask_paths],
+            axis=2,
+        )
+        background_mask = one_hot_encoded.sum(axis=2, keepdims=True) == 0
+        one_hot_encoded_with_bg = np.concatenate([background_mask, one_hot_encoded], axis=2)
+        segmentation_label = np.argmax(one_hot_encoded_with_bg, axis=2)
+        return tv_tensors.Mask(segmentation_label)
 
-    def _get_image_path(self, index: int) -> str:
+    def _get_image_path(self, sample_index: int) -> str:
         """Returns the corresponding image path."""
-        sample_dir = self._get_sample_dir(index)
+        sample_dir = self._samples_dirs[sample_index]
         return os.path.join(self._root, sample_dir, "ct.nii.gz")
 
-    def _get_sample_dir(self, index: int) -> str:
-        """Returns the corresponding sample directory."""
-        sample_index = self._indices[index // self._n_slices_per_image]
-        return self._samples_dirs[sample_index]
+    def _get_masks_dir(self, sample_index: int) -> str:
+        """Returns the directory of the corresponding masks."""
+        sample_dir = self._samples_dirs[sample_index]
+        return os.path.join(self._root, sample_dir, "segmentations")
 
-    def _get_sample_slice_index(self, index: int) -> int:
-        """Returns the corresponding slice index."""
-        image_path = self._get_image_path(index)
-        total_slices = io.fetch_total_nifti_slices(image_path)
-        slice_indices = np.linspace(0, total_slices - 1, num=self._n_slices_per_image, dtype=int)
-        return slice_indices[index % self._n_slices_per_image]
+    def _get_number_of_slices_per_sample(self, sample_index: int) -> int:
+        """Returns the total amount of slices of a sample."""
+        image_path = self._get_image_path(sample_index)
+        return io.fetch_total_nifti_slices(image_path)
 
     def _fetch_samples_dirs(self) -> List[str]:
         """Returns the name of all the samples of all the splits of the dataset."""
@@ -179,31 +178,51 @@ class TotalSegmentator2D(base.ImageSegmentation):
         ]
         return sorted(sample_filenames)
 
-    def _create_indices(self) -> List[int]:
-        """Builds the dataset indices for the specified split."""
-        split_index_ranges = {
-            "train": self._train_index_ranges,
-            "val": self._val_index_ranges,
-            None: [(0, 103)],
-        }
-        index_ranges = split_index_ranges.get(self._split)
-        if index_ranges is None:
-            raise ValueError("Invalid data split. Use 'train', 'val' or `None`.")
+    def _get_split_indices(self) -> List[int]:
+        """Returns the samples indices that corresponding the dataset split and version."""
+        key = f"{self._split}_{self._version}"
+        match key:
+            case "train_small":
+                index_ranges = [(0, 83)]
+            case "val_small":
+                index_ranges = [(83, 102)]
+            case _:
+                index_ranges = [(0, len(self._samples_dirs))]
 
         return _utils.ranges_to_indices(index_ranges)
 
+    def _create_indices(self) -> List[Tuple[int, int]]:
+        """Builds the dataset indices for the specified split.
+
+        Returns:
+            A list of tuples, where the first value indicates the
+            sample index which the second its corresponding slice
+            index.
+        """
+        indices = [
+            (sample_idx, slide_idx)
+            for sample_idx in self._get_split_indices()
+            for slide_idx in range(self._get_number_of_slices_per_sample(sample_idx))
+            if slide_idx % (self._sample_every_n_slices or 1) == 0
+        ]
+        return indices
+
     def _download_dataset(self) -> None:
         """Downloads the dataset."""
         dataset_resources = {
             "small": self._resources_small,
             "full": self._resources_full,
-            None: (0, 103),
         }
-        resources = dataset_resources.get(self._version)
+        resources = dataset_resources.get(self._version or "")
         if resources is None:
-            raise ValueError("Invalid data version. Use 'small' or 'full'.")
+            raise ValueError(
+                f"Can't download data version '{self._version}'. Use 'small' or 'full'."
+            )
 
         for resource in resources:
+            if os.path.isdir(self._root):
+                continue
+
             utils.download_and_extract_archive(
                 resource.url,
                 download_root=self._root,

eva/vision/utils/convert.py

@@ -0,0 +1,24 @@
+"""Image conversion related functionalities."""
+
+from typing import Any
+
+import numpy as np
+import numpy.typing as npt
+
+
+def to_8bit(image_array: npt.NDArray[Any]) -> npt.NDArray[np.uint8]:
+    """Casts an image of higher bit image (i.e. 16bit) to 8bit.
+
+    Args:
+        image_array: The image array to convert.
+
+    Returns:
+        The image as normalized as a 8-bit format.
+    """
+    if np.issubdtype(image_array.dtype, np.integer):
+        image_array = image_array.astype(np.float64)
+
+    image_scaled_array = image_array - image_array.min()
+    image_scaled_array /= image_scaled_array.max()
+    image_scaled_array *= 255
+    return image_scaled_array.astype(np.uint8)

eva/vision/utils/io/nifti.py

@@ -8,16 +8,19 @@ import numpy.typing as npt
 from eva.vision.utils.io import _utils
 
 
-def read_nifti_slice(path: str, slice_index: int) -> npt.NDArray[Any]:
+def read_nifti_slice(
+    path: str, slice_index: int, *, use_storage_dtype: bool = True
+) -> npt.NDArray[Any]:
     """Reads and loads a NIfTI image from a file path as `uint8`.
 
     Args:
         path: The path to the NIfTI file.
-        slice_index: The image slice index to return. If `None`, it will
-            return the full 3D image.
+        slice_index: The image slice index to return.
+        use_storage_dtype: Whether to cast the raw image
+            array to the inferred type.
 
     Returns:
-        The image as a numpy array.
+        The image as a numpy array (height, width, channels).
 
     Raises:
         FileExistsError: If the path does not exist or it is unreachable.
@@ -25,10 +28,11 @@ def read_nifti_slice(path: str, slice_index: int) -> npt.NDArray[Any]:
     """
     _utils.check_file(path)
     image_data = nib.load(path)  # type: ignore
-    dtype = image_data.get_data_dtype()  # type: ignore
     image_slice = image_data.slicer[:, :, slice_index : slice_index + 1]  # type: ignore
     image_array = image_slice.get_fdata()
-    return image_array.astype(dtype)
+    if use_storage_dtype:
+        image_array = image_array.astype(image_data.get_data_dtype())  # type: ignore
+    return image_array
 
 
 def fetch_total_nifti_slices(path: str) -> int:

{kaiko_eva-0.0.1.dist-info → kaiko_eva-0.0.2.dist-info}/METADATA

@@ -1,10 +1,10 @@
 Metadata-Version: 2.1
 Name: kaiko-eva
-Version: 0.0.1
+Version: 0.0.2
 Summary: Evaluation Framework for oncology foundation models.
-Keywords: machine-learning evaluation-framework oncology foundation-models
-Author-Email: Ioannis Gatopoulos <ioannis@kaiko.ai>, Nicolas Känzig <nicolas@kaiko.ai>, Roman Moser <roman@kaiko.ai>
-Maintainer-Email: Ioannis Gatopoulos <ioannis@kaiko.ai>, Nicolas Känzig <nicolas@kaiko.ai>, Roman Moser <roman@kaiko.ai>
+Keywords: machine-learning,evaluation-framework,oncology,foundation-models
+Author-Email: Ioannis Gatopoulos <ioannis@kaiko.ai>, =?utf-8?q?Nicolas_K=C3=A4nzig?= <nicolas@kaiko.ai>, Roman Moser <roman@kaiko.ai>
+Maintainer-Email: Ioannis Gatopoulos <ioannis@kaiko.ai>, =?utf-8?q?Nicolas_K=C3=A4nzig?= <nicolas@kaiko.ai>, Roman Moser <roman@kaiko.ai>
 License:                                  Apache License
                                    Version 2.0, January 2004
                                 http://www.apache.org/licenses/
@@ -215,15 +215,17 @@ Project-URL: Homepage, https://kaiko-ai.github.io/eva/dev/
 Project-URL: Repository, https://github.com/kaiko-ai/eva
 Project-URL: Documentation, https://kaiko-ai.github.io/eva/dev/
 Requires-Python: >=3.10
-Requires-Dist: lightning>=2.2.1
-Requires-Dist: jsonargparse[omegaconf]>=4.27.4
+Requires-Dist: torch==2.3.0
+Requires-Dist: lightning>=2.2.2
+Requires-Dist: jsonargparse[omegaconf]==4.28
 Requires-Dist: tensorboard>=2.16.2
 Requires-Dist: loguru>=0.7.2
 Requires-Dist: pandas>=2.2.0
 Requires-Dist: transformers>=4.38.2
 Requires-Dist: onnxruntime>=1.17.1
-Requires-Dist: onnx>=1.15.0
+Requires-Dist: onnx>=1.16.0
 Requires-Dist: toolz>=0.12.1
+Requires-Dist: rich>=13.7.1
 Requires-Dist: h5py>=3.10.0; extra == "vision"
 Requires-Dist: nibabel>=5.2.0; extra == "vision"
 Requires-Dist: opencv-python-headless>=4.9.0.80; extra == "vision"
@@ -240,15 +242,19 @@ Description-Content-Type: text/markdown
 
 <div align="center">
 
-<img src="https://github.com/kaiko-ai/eva/blob/main/docs/images/eva-logo.png?raw=true" width="400">
+<br />
+
+<img src="https://github.com/kaiko-ai/eva/blob/main/docs/images/eva-logo.png?raw=true" width="340">
 
+<br />
 <br />
 
 _Oncology FM Evaluation Framework by kaiko.ai_
 
 [![PyPI](https://img.shields.io/pypi/v/kaiko-eva.svg?logo=python)](https://pypi.python.org/pypi/kaiko-eva)
-[![CI](https://github.com/kaiko-ai/eva/workflows/CI/badge.svg)](https://github.com/kaiko-ai/eva/actions?query=workflow%3ACI)
-[![license](https://img.shields.io/badge/License-Apache%202.0-blue.svg?labelColor=gray)](https://github.com/kaiko-ai/eva#license)
+[![docs](https://img.shields.io/badge/📚_docs-latest-green)](https://kaiko-ai.github.io/eva/latest)
+[![license](https://img.shields.io/badge/⚖️_License-Apache%202.0-blue.svg?labelColor=gray)](https://github.com/kaiko-ai/eva#license)<br>
+[![paper](http://img.shields.io/badge/OpenReview-MIDL_2024-B31B1B.svg)](https://openreview.net/forum?id=FNBQOPj18N&noteId=FNBQOPj18N)
 
 <p align="center">
   <a href="https://github.com/kaiko-ai/eva#installation">Installation</a> •
@@ -299,18 +305,18 @@ eva --version
 
 ## How To Use
 
-_eva_ can be used directly from the terminal as a CLI tool as follows:
+_`eva`_ can be used directly from the terminal as a CLI tool as follows:
 ```sh
 eva {fit,predict,predict_fit} --config url/or/path/to/the/config.yaml 
 ```
 
-When used as a CLI tool, `_eva_` supports configuration files (`.yaml`) as an argument to define its functionality.
+When used as a CLI tool, _`eva`_ supports configuration files (`.yaml`) as an argument to define its functionality.
 Native supported configs can be found at the [configs](https://github.com/kaiko-ai/eva/tree/main/configs) directory
 of the repo. Apart from cloning the repo, you can download the latest config folder as `.zip` from your browser from
 [here](https://download-directory.github.io/?url=https://github.com/kaiko-ai/eva/tree/main/configs). Alternatively,
 from a specific release the configs can be downloaded from the terminal as follows:
 ```sh
-curl -LO https://github.com/kaiko-ai/eva/releases/download/0.0.1/configs.zip | unzip configs.zip
+curl -LO https://github.com/kaiko-ai/eva/releases/download/0.0.1/configs.zip | unzip configs
 ```
 
 For example, to perform a downstream evaluation of DINO ViT-S/16 on the BACH dataset with
@@ -338,7 +344,7 @@ and [tutorials](https://kaiko-ai.github.io/eva/dev/user-guide/advanced/replicate
 
 ## Benchmarks
 
-In this section you will find model benchmarks which were generated with _eva_.
+In this section you will find model benchmarks which were generated with _`eva`_.
 
 ### Table I: WSI patch-level benchmark
 
@@ -351,13 +357,15 @@ In this section you will find model benchmarks which were generated with _eva_.
 | ViT-S/16 _(random)_	<sup>[1]</sup>               | 0.410 | 0.617 | 0.501 | 0.753    | 0.728     |
 | ViT-S/16 _(ImageNet)_ <sup>[1]</sup>             | 0.695 | 0.935 | 0.831 | 0.864    | 0.849     |
 | ViT-B/8 _(ImageNet)_ <sup>[1]</sup>              | 0.710 | 0.939 | 0.814 | 0.870    | 0.856     |
+| ViT-L/14 _(ImageNet)_ <sup>[1]</sup>             | 0.707 | 0.916 | 0.832 | 0.873    | 0.888     |
 | DINO<sub>(p=16)</sub> <sup>[2]</sup>             | 0.801 | 0.934 | 0.768 | 0.889    | 0.895     |
 | Phikon <sup>[3]</sup>                            | 0.725 | 0.935 | 0.777 | 0.912    | 0.915     |
-| ViT-S/16 _(kaiko.ai)_ <sup>[4]</sup>             | 0.797 | 0.943 | 0.828 | 0.903    | 0.893     |
-| ViT-S/8 _(kaiko.ai)_ <sup>[4]</sup>              | 0.834 | 0.946 | 0.832 | 0.897    | 0.887     |
-| ViT-B/16 _(kaiko.ai)_	<sup>[4]</sup>             | 0.810 | 0.960 | 0.826 | 0.900    | 0.898     |
-| ViT-B/8 _(kaiko.ai)_ <sup>[4]</sup>              | 0.865 | 0.956 | 0.809 | 0.913    | 0.921     |
-| ViT-L/14 _(kaiko.ai)_ <sup>[4]</sup>             | 0.870 | 0.930 | 0.809 | 0.908    | 0.898     |
+| UNI <sup>[4]</sup>                               | 0.814 | 0.950 | 0.837 | 0.936    | 0.938     |
+| ViT-S/16 _(kaiko.ai)_ <sup>[5]</sup>             | 0.797 | 0.943 | 0.828 | 0.903    | 0.893     |
+| ViT-S/8 _(kaiko.ai)_ <sup>[5]</sup>              | 0.834 | 0.946 | 0.832 | 0.897    | 0.887     |
+| ViT-B/16 _(kaiko.ai)_	<sup>[5]</sup>             | 0.810 | 0.960 | 0.826 | 0.900    | 0.898     |
+| ViT-B/8 _(kaiko.ai)_ <sup>[5]</sup>              | 0.865 | 0.956 | 0.809 | 0.913    | 0.921     |
+| ViT-L/14 _(kaiko.ai)_ <sup>[5]</sup>             | 0.870 | 0.930 | 0.809 | 0.908    | 0.898     |
 
 _Table I: Linear probing evaluation of FMs on patch-level downstream datasets.<br> We report averaged balanced accuracy
 over 5 runs, with an average standard deviation of ±0.003._
@@ -367,14 +375,15 @@ over 5 runs, with an average standard deviation of ±0.003._
 <br />
 
 _References_:
-1. _"Emerging properties in self-supervised vision transformers”_
-2. _"Benchmarking self-supervised learning on diverse pathology datasets”_
-3. _"Scaling self-supervised learning for histopathology with masked image modeling”_
-4. _"Towards Training Large-Scale Pathology Foundation Models: from TCGA to Hospital Scale”_
+1. _"Emerging properties in self-supervised vision transformers”_, [arXiv](https://arxiv.org/abs/2104.14294)
+2. _"Benchmarking self-supervised learning on diverse pathology datasets”_, [arXiv](https://arxiv.org/abs/2212.04690)
+3. _"Scaling self-supervised learning for histopathology with masked image modeling”_, [medRxiv](https://www.medrxiv.org/content/10.1101/2023.07.21.23292757v1)
+4. _"A General-Purpose Self-Supervised Model for Computational Pathology”_, [arXiv](https://arxiv.org/abs/2308.15474)
+5. _"Towards Training Large-Scale Pathology Foundation Models: from TCGA to Hospital Scale”_, [arXiv](https://arxiv.org/pdf/2404.15217)
 
 ## Contributing
 
-_eva_ is an open source project and welcomes contributions of all kinds. Please checkout the [developer](./docs/DEVELOPER_GUIDE.md)
+_`eva`_ is an open source project and welcomes contributions of all kinds. Please checkout the [developer](./docs/DEVELOPER_GUIDE.md)
 and [contributing guide](./docs/CONTRIBUTING.md) for help on how to do so.
 
 All contributors must follow the [code of conduct](./docs/CODE_OF_CONDUCT.md).
@@ -399,7 +408,24 @@ Our codebase is built using multiple opensource contributions
 
 </div>
 
----
+
+## Citation
+
+If you find this repository useful, please consider giving a star ⭐ and adding the following citation:
+
+```
+@inproceedings{
+kaiko.ai2024eva,
+title={eva: Evaluation framework for pathology foundation models},
+author={kaiko.ai and Ioannis Gatopoulos and Nicolas K{\"a}nzig and Roman Moser and Sebastian Ot{\'a}lora},
+booktitle={Medical Imaging with Deep Learning},
+year={2024},
+url={https://openreview.net/forum?id=FNBQOPj18N}
+}
+```
+
+<br />
+
 <div align="center">
   <img src="https://github.com/kaiko-ai/eva/blob/main/docs/images/kaiko-logo.png?raw=true" width="200">
 </div>

{kaiko_eva-0.0.1.dist-info → kaiko_eva-0.0.2.dist-info}/RECORD

@@ -1,8 +1,10 @@
+eva/.DS_Store,sha256=nHFfks7iwDvTdxEQbx3nJ4A8L95xoUm4jl5emHwGusQ,6148
 eva/__init__.py,sha256=bYBwklT7diG8NBIBDbpwjN4RUsvGv0ShWBXPxWgz404,518
 eva/__main__.py,sha256=kM5tQ0egTuBWixNLLx9QU-PpS2Bbs3zE3nYE6b2vWa0,282
 eva/__version__.py,sha256=YFR4oOlvPg0sS4Ni7GJ_vU42VTs5WiWp6odK7yH4TBY,611
 eva/core/__init__.py,sha256=AYlMZcH76B7I1lOa-E67u2o9DxsCwI4JMLCYXLk9oDQ,451
-eva/core/callbacks/__init__.py,sha256=tglEHfVB0NSaXenNLQAlyb2ufXiamxfR0o15W9a9t0k,110
+eva/core/callbacks/__init__.py,sha256=tHC6HJkLMKI5ThuSOuk3XLMvym4v2EtlDqrT91aAdmg,191
+eva/core/callbacks/config.py,sha256=-DRt20a2aF9Z9-7nZvbGBcOZ30qNf3ESf25EPRgRL1w,4267
 eva/core/callbacks/writers/__init__.py,sha256=GG8UXkbgNmpN1u_YIw-QysBGTSFm6C-P2XRtfnvVBrY,121
 eva/core/callbacks/writers/embeddings.py,sha256=q8Gd2_aDhhD7-QT5xAJbm8ikNjmHq_2DJosJ6WS5BOo,6752
 eva/core/callbacks/writers/typings.py,sha256=5AVIRAftqPTlLQ8s4ArEcMgLCyPnCZ9FFNk2yFppA1g,616
@@ -17,18 +19,31 @@ eva/core/data/datamodules/__init__.py,sha256=qZchYbgxo9lxYnGoqdk0C6MfS2IbF0WItO0
 eva/core/data/datamodules/call.py,sha256=jjj9w3UXYuQB-qyCcw1EZpRJW10OC1I3dvgvsuQWLck,940
 eva/core/data/datamodules/datamodule.py,sha256=dclC2YJAXUGEUpV9ZRWQS43-ksFIPgVeFudsyrj9kdc,3878
 eva/core/data/datamodules/schemas.py,sha256=EXnUPNd9Pj3RjnxJIzAcC2qp6TtBSvPDx28fV_ovWAA,1869
-eva/core/data/datasets/__init__.py,sha256=pMU-w6aQoRFgSwPB9GLXNilnsbwd6HqLlgw49e4rlj0,281
+eva/core/data/datasets/__init__.py,sha256=Y_18JE9sDtwEFdgPiKHf_ZqMj_1SUQtRZeiI2n7t1uA,387
 eva/core/data/datasets/base.py,sha256=NLZlxznB4SCYNf070OhfNJztaOpqwQWemwpGkFv_CA0,2005
-eva/core/data/datasets/classification/__init__.py,sha256=nhgeoK0chIvX9kzrp9yz40xha_g78o-R4AV7HbyfQOU,176
-eva/core/data/datasets/classification/embeddings.py,sha256=E2vYX5q0wDueIZwfB252aM4l9i8XNuf2BQ1lOJR32P4,5215
 eva/core/data/datasets/dataset.py,sha256=tA6Wd_7vqOE9GsukSWrgN9zaZKtKCHaE58SqIfWxWdg,124
+eva/core/data/datasets/embeddings/__init__.py,sha256=kxJtohGI6oP2lJiDVb61w7NMXuVD3np2B5wbuMIu6K4,357
+eva/core/data/datasets/embeddings/base.py,sha256=EXGa4qsXMA1LkdcZEdjnQq-ooSdw2VitjvpZLcTB8ug,4979
+eva/core/data/datasets/embeddings/classification/__init__.py,sha256=E2zyht5De7RnTVF-MRbteCzdUt4_Of2zJx3jolPpCdM,371
+eva/core/data/datasets/embeddings/classification/embeddings.py,sha256=d5s9f58oQKuRyzWGAg2RXFG41NjLWqu56O3_CI77S_8,2467
+eva/core/data/datasets/embeddings/classification/multi_embeddings.py,sha256=737KakBBui3zvMWKqoXWIG_qa5yaxhgtGP_iBCKnnPY,4343
 eva/core/data/samplers/__init__.py,sha256=WikBo1DemCx6o2vFfNwSwODlmCT2zWUXtCNwiWCVAFE,100
 eva/core/data/samplers/sampler.py,sha256=vrrXERWC67fjmTk_uwD7s9-8-rdhvnx7OlSipHE6sdY,119
-eva/core/data/transforms/__init__.py,sha256=ZdqOER1VMLu5nI1As0IuBPTS8ISw0EO4zeMZoio3G-c,157
+eva/core/data/transforms/__init__.py,sha256=n0TczmJSc9EjR6JezAZqlZIN4Gz_X3UBePbyDSC7JkE,308
 eva/core/data/transforms/dtype/__init__.py,sha256=r_LM_hdh_gTsrgh3shDTdMpu-lgQNHJ1yD6wY3omPyg,174
 eva/core/data/transforms/dtype/array.py,sha256=RDSkXlnSHSYyU_gv7vw33OZ7vhEy62PQGoE3htGGaqc,725
+eva/core/data/transforms/padding/__init__.py,sha256=AKSXa2dOhj45dTw81piPoCfDmIL0FPJUIxZ3HlG7KVM,138
+eva/core/data/transforms/padding/pad_2d_tensor.py,sha256=J4maGFmeQf9IHRxt5kU-6eI-Bvk12F_HVk8kR_omrnY,1185
+eva/core/data/transforms/sampling/__init__.py,sha256=BFKbvRjlZrwS0GcNrM54ZSWt6PrQARfFlXM1jJ-wpvo,149
+eva/core/data/transforms/sampling/sample_from_axis.py,sha256=Zbhp94lVa70WQKmSOKMTsOMe2c7wLqNZto7JqWhSdtI,1229
 eva/core/interface/__init__.py,sha256=chdpKXipxe1NP-Fgr_d9r6X1gMna0XiEa38waJ6FzTM,98
 eva/core/interface/interface.py,sha256=GzjneNHhTIEuLbydUG9cSmpHjJ4_IENGM-glN8RaRxY,2741
+eva/core/loggers/__init__.py,sha256=4YMLNlN9LnuKqhBI1R1keh69dmMD-2lcH3HKwwyn380,266
+eva/core/loggers/dummy.py,sha256=Y7ypH0ecSAIkkZ5LzTmNNEzlKkqeaHfUNMCDKVOg6D4,1204
+eva/core/loggers/experimental_loggers.py,sha256=JjW_SAABnNZyhJEy6kcPkPKDPyvuAj4sQTdn-tewm8U,204
+eva/core/loggers/log/__init__.py,sha256=cPqLKqIUhiTeDNG5ZUUOExDr76y4LBe4yXUvCxIQh0o,124
+eva/core/loggers/log/parameters.py,sha256=7qxa-ndtYb2_UkPZ4AlcHaGeUvEw2_9phCdco_OZ9Oo,1413
+eva/core/loggers/log/utils.py,sha256=k4Q7uKpAQctfDv0EEYPnPv6wt9LnckEeqGvbYSLfKO0,415
 eva/core/metrics/__init__.py,sha256=sTpNUbvgpKTd1IifzPVWmXVZ17PSJjcfEAlY_3fZP5U,558
 eva/core/metrics/average_loss.py,sha256=AyFOnCXBD5T62eSYf6eGAAJsqt8x-KaHgc8OLkCHjzE,1267
 eva/core/metrics/binary_balanced_accuracy.py,sha256=MabsXAtVfLqSaSIIpE0HIM6bo8uRszl6obueHI6vJi0,806
@@ -44,9 +59,9 @@ eva/core/metrics/structs/schemas.py,sha256=S6dTbz6YjxkNUIqWVd52KgpVx5JqNFqM4Xs7z
 eva/core/metrics/structs/typings.py,sha256=qJd-FiD2IhJgBeo8FyP0vpVUIH4RKb1k6zYvHtjUA04,388
 eva/core/models/__init__.py,sha256=yRLRKYuShhgQBWzV6sjzjThOqqNb9HRS48bMmAxEy-8,305
 eva/core/models/modules/__init__.py,sha256=QJWJ42BceXZBzDGgk5FHBcCaRrB9egTFKVF6gDsBYfM,255
-eva/core/models/modules/head.py,sha256=Rn9bJmSRWqNPnRl-YpvPZgtjbr6UNU83oHXQ1gEpAJE,4138
+eva/core/models/modules/head.py,sha256=sJ2RTNmOsqpCczajwgp6nHZ5qELhjEs8BhO36KyDG-g,3992
 eva/core/models/modules/inference.py,sha256=ih-0Rr2oNf2N6maiXPOW7XH5KVwUT1_MOxnJKOhJ1uQ,978
-eva/core/models/modules/module.py,sha256=0KquNWeblYg49S8AoV-Dpc65_ZIWl56ht5R7bKKXj7o,5918
+eva/core/models/modules/module.py,sha256=7mCzyvBNOWhvN8sNa91yB79iSBlJlYh9sypL37Nwdes,6836
 eva/core/models/modules/typings.py,sha256=fNoGsC_q1d9c2KauUC-f1psKrCFmfoeC8JJ_US_pOW0,521
 eva/core/models/modules/utils/__init__.py,sha256=pnbxlEhT87JimWNr-NSNCv7VNR-IyDi_A9qRWmvlzwQ,227
 eva/core/models/modules/utils/batch_postprocess.py,sha256=q1kC3pwSS7RyI76qunuvFP7RpUhEpUsR6xzjahJkQKQ,1915
@@ -63,10 +78,10 @@ eva/core/models/networks/wrappers/huggingface.py,sha256=81j0pcEx3DW6gR-81Fz6tZkJ
 eva/core/models/networks/wrappers/onnx.py,sha256=LZEGOpg1VYrB3wXMAA5IMfiKNTkOXQ50agHjTvYnnsU,1718
 eva/core/trainers/__init__.py,sha256=jhsKJF7HAae7EOiG3gKIAHH_h3dZlTE2JRcCHJmOzJc,208
 eva/core/trainers/_logging.py,sha256=gi4FqPy2GuVmh0WZY6mYwF7zMPvnoFA050B0XdCP6PU,2571
-eva/core/trainers/_recorder.py,sha256=_Vfp7Njh_9qP-SWbBGYp8solnfFgIUi2Z9pGLXt52WY,5652
+eva/core/trainers/_recorder.py,sha256=y6i5hfXftWjeV3eQHmMjUOkWumnZ2QNv_u275LLmvPA,7702
 eva/core/trainers/_utils.py,sha256=M3h8lVhUmkeSiEXpX9hRdMvThGFCnTP15gv-hd1CZkc,321
-eva/core/trainers/functional.py,sha256=pIeGXoO63Wh6n1mOYlBo5ACCteGuNV9pZhqxfN4RLSs,3775
-eva/core/trainers/trainer.py,sha256=j4rYWiG9COxBbZ6WIlpRPBE153XqlYK7eAWlRsZgljU,3261
+eva/core/trainers/functional.py,sha256=Ju0Eh98oxsj_7QBwxu3GddCD7FROEdQgpp9fdGS9sp4,4360
+eva/core/trainers/trainer.py,sha256=Vw_KhTyh-3YV5qo_XHxz9oy-v2PxrgoOWMeYi8-41R0,3949
 eva/core/utils/__init__.py,sha256=F1C69M9y7W8qh1J2k-X4frRHa7r1mPXewscC94fFYtk,58
 eva/core/utils/io/__init__.py,sha256=SAME0kuSvDE1DKFJwMBmnCkpDAy4ujXuRTSJsHNhwUI,112
 eva/core/utils/io/dataframe.py,sha256=CIHFowljH17waDkJ9YJVEVXAIcxMwoLjUgoBttiNk8w,509
@@ -74,37 +89,39 @@ eva/core/utils/multiprocessing.py,sha256=PxUxMyvI62lghyWF46O5RNL-J7DUR2IrXSwdkbh
 eva/core/utils/workers.py,sha256=hfx63M82qNg0Dwhre2tl53MnhtRsV7APaDONM9nhVB8,634
 eva/vision/__init__.py,sha256=Z9AuPmTO-i73pUtq3IkZzwRlY1E5xCE8IZiyl5S71TM,438
 eva/vision/data/__init__.py,sha256=aoKPmX8P2Q2k2W3nlq8vFU41FV6Sze-0SDuWtU-ETh4,111
-eva/vision/data/datasets/__init__.py,sha256=aV4qPqtlt0PnaGoxUW_xEwAr8b8ddkl_YE4_fAdavds,497
-eva/vision/data/datasets/_utils.py,sha256=5GAZEHn-VezxTXaW1jVZO5zvdVl1Vz8_5gV2qkoMu4s,1414
+eva/vision/data/datasets/__init__.py,sha256=0pGqI6m4zUEwHPFHcE_7z2MsDS7hG9xL8mnXvSPklOo,402
+eva/vision/data/datasets/_utils.py,sha256=epPcaYE4w2_LtUKLLQJh6qQxUNVBe22JA06k4WUerYQ,1430
 eva/vision/data/datasets/_validators.py,sha256=uPbbUNnftb8mYzsKVrF-ZX_xinB2zQkuQLFYMprVjhY,2099
-eva/vision/data/datasets/classification/__init__.py,sha256=I9vTkETzGnTNNvyRB96ut1YHx9ARmZVO0-0l3ZLWEAs,520
+eva/vision/data/datasets/classification/__init__.py,sha256=DZq9__B4D2x1fbQsG-SwcOR_KF8ZFgCtwTzhC16p63c,362
 eva/vision/data/datasets/classification/bach.py,sha256=_xuA4evV9jCI76bUKbzom4ECLKShCsd95S8PtvhRAH4,5637
 eva/vision/data/datasets/classification/base.py,sha256=zBqn8rQP59j1DEChf3rDXgyMtB_sbug8kPvgFCqZyl4,3060
 eva/vision/data/datasets/classification/crc.py,sha256=7RR0PJWnhLMa3AUB_F2XMYawF5gnCNbGMv25ejOEeNA,5875
 eva/vision/data/datasets/classification/mhist.py,sha256=yoDHZ2vqa26YKVvJ9t6aidOVGazGIwUD6F3o0zNsxjM,3257
 eva/vision/data/datasets/classification/patch_camelyon.py,sha256=CH9sveoMppNWPQHm4qPTONRSGqX3O8P3OYwMB6mO678,7253
-eva/vision/data/datasets/classification/total_segmentator.py,sha256=OkbqS41ykdUX0wGf6jSja5WzeeRmevUnH5alfcEQhwg,8069
 eva/vision/data/datasets/segmentation/__init__.py,sha256=byQCBHicM6mQkljHPllUqRvoFaJxHtPMKcyjPmK6dUM,249
-eva/vision/data/datasets/segmentation/base.py,sha256=JogXJ3KiOaUybAcyvoqjR4yjlBfVTt2Rt8OOAz32Jrc,3630
-eva/vision/data/datasets/segmentation/total_segmentator.py,sha256=NUh-NlrsTcUsbe3qLd_d481mok970bNF7zIdpAS7eks,8075
+eva/vision/data/datasets/segmentation/base.py,sha256=XSD-hl7UtqshzF9ulImlL7v11lT2rWhhro7K3dF0Ucs,2937
+eva/vision/data/datasets/segmentation/total_segmentator.py,sha256=xKGQN03ybOXQE1EtO9WRnAZ_8B40uXtaz2WliNFJ4Uc,8705
 eva/vision/data/datasets/structs.py,sha256=RaTDW-B36PumcR5gymhCiX-r8GiKqIFcjqoEEjjFyUE,389
 eva/vision/data/datasets/vision.py,sha256=hKKFMb65UJQzOyYm8FTGkOGBOinMRu7R8sOFMbCmQX4,1100
 eva/vision/data/transforms/__init__.py,sha256=cHnLwyx6biAjqstD4IDspVtM-_dv7GBrQG6x_0SM8MM,120
 eva/vision/data/transforms/common/__init__.py,sha256=ZHzpdr-THc9CgFFbAVMWUiZrUNUiHnCDM8GYhM7tMfU,138
 eva/vision/data/transforms/common/resize_and_crop.py,sha256=IkAeTOe5TxK_cHzFvS7yW8YUh27C-KjXqekL7pfcT9A,1485
+eva/vision/models/.DS_Store,sha256=CKEtWIsQcwe9BwZ8pyCnXleWpY_4ilCps_OuRG9ZGaM,8196
 eva/vision/models/__init__.py,sha256=v9JhyLdy38XUkA0JmNMzSxNYmKi7nWBrp_XYgM7dmTU,89
+eva/vision/models/networks/.DS_Store,sha256=1lFlJ5EFymdzGAUAaI30vcaaLHt3F1LwpG7xILf9jsM,6148
 eva/vision/models/networks/__init__.py,sha256=IDpFsocWtyfe28vR9yMmXPYzV9X2NSDrTx7ewH8u-XU,170
 eva/vision/models/networks/abmil.py,sha256=N1eH4fn1nXmgXurSQyQIxxonv7nsqeeuPWaQSHeltfs,6796
 eva/vision/models/networks/postprocesses/__init__.py,sha256=nWBuROKE77W9xfyAxmS6L9IgOaXjcB5Qpaw1ihHG64E,148
 eva/vision/models/networks/postprocesses/cls.py,sha256=AFRrCjSmKy0n14toKa-G-QVx3dh-H4zSx5myi_P2OFA,822
 eva/vision/utils/__init__.py,sha256=vaUovprE743SmyFH8l6uk4pYSWpI4zxn7lN0EwePTJI,96
+eva/vision/utils/convert.py,sha256=tP0ps_IK2BXkuUsmI0UXVrSbmDAbjfLtQt3AiFtT2j4,679
 eva/vision/utils/io/__init__.py,sha256=Aw2UxGO3nbUidroMlS-MMJUALjQVvfsOZ1ZhcENDwRo,310
 eva/vision/utils/io/_utils.py,sha256=JzOt7Frj6ScF_aNjFtfHBn4ROnl6NhUZucmQhLc4Cww,768
 eva/vision/utils/io/image.py,sha256=2jzeVFMvIRhuTkIrQeLyu0y8GttLp6rWRjO9I2uw-I8,1489
-eva/vision/utils/io/nifti.py,sha256=ph9w8dNNSsJG2wI3NJNPTLyWdz2S0i9jD068nHXVVJs,1510
+eva/vision/utils/io/nifti.py,sha256=Rfbz49IakkAMimN8VnHJxDgxqTVwxGfxWFrTMXLrbJc,1659
 eva/vision/utils/io/text.py,sha256=uECChKjeKi4KQ-NqdO7ywAFS_TOEp2DQ5QQcuG8cb-4,472
-kaiko_eva-0.0.1.dist-info/METADATA,sha256=ftjXJlWbHwUT3YNSBxtaMClK_iUHh95oHl0POcZVNCA,22362
-kaiko_eva-0.0.1.dist-info/WHEEL,sha256=N2J68yzZqJh3mI_Wg92rwhw0rtJDFpZj9bwQIMJgaVg,90
-kaiko_eva-0.0.1.dist-info/entry_points.txt,sha256=oqtS2Yt5EBY4saLyCBC3Zev3huCORKTKWyPovX7QR8g,73
-kaiko_eva-0.0.1.dist-info/licenses/LICENSE,sha256=e6AEzr7j_R-PYr2qLO-JwLn8y70jbVD3U2mxbRmwcI4,11338
-kaiko_eva-0.0.1.dist-info/RECORD,,
+kaiko_eva-0.0.2.dist-info/METADATA,sha256=R4SakGonLZsdyj2yEgkkOa1Z96INt2AfP6Gvak8eN68,23562
+kaiko_eva-0.0.2.dist-info/WHEEL,sha256=vnE8JVcI2Wz7GRKorsPArnBdnW2SWKWGow5gu5tHlRU,90
+kaiko_eva-0.0.2.dist-info/entry_points.txt,sha256=oqtS2Yt5EBY4saLyCBC3Zev3huCORKTKWyPovX7QR8g,73
+kaiko_eva-0.0.2.dist-info/licenses/LICENSE,sha256=e6AEzr7j_R-PYr2qLO-JwLn8y70jbVD3U2mxbRmwcI4,11338
+kaiko_eva-0.0.2.dist-info/RECORD,,

{kaiko_eva-0.0.1.dist-info → kaiko_eva-0.0.2.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: pdm-backend (2.1.8)
+Generator: pdm-backend (2.3.0)
 Root-Is-Purelib: true
 Tag: py3-none-any

eva/core/data/datasets/classification/__init__.py

@@ -1,5 +0,0 @@
-"""Classification datasets API."""
-
-from eva.core.data.datasets.classification.embeddings import EmbeddingsClassificationDataset
-
-__all__ = ["EmbeddingsClassificationDataset"]