Merge pull request #27 from orobix/hotfix/wrong-extension-handling-an…

…omaly

Hotfix/wrong extension handling anomaly

CHANGELOG.md

@@ -2,6 +2,16 @@
 # Changelog
 All notable changes to this project will be documented in this file.
 
+### [1.0.2]
+
+#### Fixed
+
+- Fix anomaly detection training not working when images with non lowercase allowed extension are used (e.g. .BMP)
+
+#### Added
+
+- Increase the number of available extensions for classification and anomaly detection training.
+
 ### [1.0.1]
 
 #### Fixed

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "quadra"
-version = "1.0.1"
+version = "1.0.2"
 description = "Deep Learning experiment orchestration library"
 authors = [
   {name = "Alessandro Polidori", email = "[email protected]"},
@@ -115,7 +115,7 @@ repository = "https://github.com/orobix/quadra"
 
 # Adapted from https://realpython.com/pypi-publish-python-package/#version-your-package
 [tool.bumpver]
-current_version = "1.0.1"
+current_version = "1.0.2"
 version_pattern = "MAJOR.MINOR.PATCH"
 commit_message  = "build: Bump version {old_version} -> {new_version}"
 commit          = true

quadra/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "1.0.1"
+__version__ = "1.0.2"
 
 
 def get_version():

quadra/datamodules/base.py

@@ -12,7 +12,7 @@
 from quadra.utils import utils
 
 log = utils.get_logger(__name__)
-IMAGE_EXTENSIONS: List[str] = [".jpg", ".jpeg", ".png", ".ppm", ".bmp", ".pgm", ".tif"]
+IMAGE_EXTENSIONS: List[str] = [".png", ".jpg", ".jpeg", ".bmp", ".tiff", ".tif", ".pbm", ".pgm", ".ppm", ".pxm", ".pnm"]
 TrainDataset = Union[torch.utils.data.Dataset, Sequence[torch.utils.data.Dataset]]
 ValDataset = Union[torch.utils.data.Dataset, Sequence[torch.utils.data.Dataset]]
 TestDataset = torch.utils.data.Dataset

quadra/datasets/anomaly.py

@@ -11,6 +11,8 @@
 from torch import Tensor
 from torch.utils.data import Dataset
 
+from quadra.datamodules.base import IMAGE_EXTENSIONS
+
 
 def create_validation_set_from_test_set(samples: DataFrame, seed: int = 0) -> DataFrame:
     """Craete Validation Set from Test Set.
@@ -130,11 +132,11 @@ def make_anomaly_dataset(
     Returns:
         An output dataframe containing samples for the requested split (ie., train or test)
     """
-    ext = [".png", ".jpg", ".jpeg", ".bmp", ".tiff", ".tif"]
-    samples_list = []
-
-    for e in ext:
-        samples_list.extend([(str(path),) + filename.parts[-3:] for filename in path.glob(f"**/*{e}")])
+    samples_list = [
+        (str(path),) + filename.parts[-3:]
+        for filename in path.glob("**/*")
+        if filename.is_file() and os.path.splitext(filename)[-1].lower() in IMAGE_EXTENSIONS
+    ]
 
     if len(samples_list) == 0:
         raise RuntimeError(f"Found 0 images in {path}")