Add the new split logic to kolektor

Signed-off-by: Samet Akcay <[email protected]>

Author: samet-akcay

src/anomalib/data/datamodules/image/kolektor.py

@@ -23,7 +23,7 @@
 from anomalib import TaskType
 from anomalib.data.datamodules.base.image import AnomalibDataModule
 from anomalib.data.datasets.image.kolektor import KolektorDataset
-from anomalib.data.utils import DownloadInfo, Split, TestSplitMode, ValSplitMode, download_and_extract
+from anomalib.data.utils import DownloadInfo, Split, SplitMode, TestSplitMode, ValSplitMode, download_and_extract
 
 logger = logging.getLogger(__name__)
 
@@ -67,10 +67,10 @@ def __init__(
         eval_batch_size: int = 32,
         num_workers: int = 8,
         task: TaskType | str = TaskType.SEGMENTATION,
-        test_split_mode: TestSplitMode | str = TestSplitMode.FROM_DIR,
-        test_split_ratio: float = 0.2,
-        val_split_mode: ValSplitMode | str = ValSplitMode.SAME_AS_TEST,
-        val_split_ratio: float = 0.5,
+        test_split_mode: SplitMode | TestSplitMode | str = SplitMode.PREDEFINED,
+        test_split_ratio: float | None = None,
+        val_split_mode: SplitMode | ValSplitMode | str = SplitMode.AUTO,
+        val_split_ratio: float | None = None,
         seed: int | None = None,
     ) -> None:
         super().__init__(
@@ -99,6 +99,11 @@ def _setup(self, _stage: str | None = None) -> None:
             root=self.root,
         )
 
+        # Kolektor dataset does not provide a validation set.
+        # Auto behaviour is to clone the test set as validation set.
+        if self.val_split_mode == SplitMode.AUTO:
+            self.val_data = self.test_data.clone()
+
     def prepare_data(self) -> None:
         """Download the dataset if not available.
 

src/anomalib/data/datasets/image/mvtec.py

@@ -25,7 +25,6 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-import logging
 from collections.abc import Sequence
 from pathlib import Path
 
@@ -37,9 +36,6 @@
 from anomalib.data.errors import MisMatchError
 from anomalib.data.utils import LabelName, Split, validate_path
 
-logger = logging.getLogger(__name__)
-
-
 IMG_EXTENSIONS = (".png", ".PNG")
 CATEGORIES = (
     "bottle",