Cache test datasets

Signed-off-by: Beat Buesser <[email protected]>

Author: beat-buesser

.github/workflows/ci-style-checks.yml

@@ -28,32 +28,40 @@ jobs:
     steps:
       - name: Checkout Repo
         uses: actions/checkout@v4
+
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
           python-version: '3.10'
+
       - name: Pre-install
         run: |
           sudo apt-get update
           sudo apt-get -y -q install ffmpeg libavcodec-extra
+
       - name: Install Dependencies
         run: |
           python -m pip install --upgrade pip setuptools wheel
           pip install -q -r <(sed '/^tensorflow/d;/^keras/d' requirements_test.txt)
           pip install tensorflow==2.18.1
           pip install keras==3.10.0
           pip list
+
       - name: pycodestyle
         run: pycodestyle --ignore=C0330,C0415,E203,E231,W503 --max-line-length=120 art
+
       - name: pylint
         if: ${{ always() }}
         run: pylint --fail-under=9.6 art/
+
       - name: mypy
         if: ${{ always() }}
         run: mypy art
+
       - name: ruff
         if: ${{ always() }}
         run: ruff check art/ tests/ examples/
+
       - name: black
         if: ${{ always() }}
         run: |

art/utils.py

@@ -1600,14 +1600,15 @@ def get_file(
     if not os.path.exists(path_):
         os.makedirs(path_)
 
+    target_path = os.path.join(path_, filename)
+
     if extract:
-        extract_path = os.path.join(path_, filename)
-        full_path = extract_path + ".tar.gz"
+        full_path = target_path + ".tar.gz"
     else:
-        full_path = os.path.join(path_, filename)
+        full_path = target_path
 
     # Determine if dataset needs downloading
-    download = not os.path.exists(full_path)
+    download = not os.path.exists(target_path)
 
     if download:
         logger.info("Downloading data from %s", url)
@@ -1655,9 +1656,9 @@ def progress_bar(blocks: int = 1, block_size: int = 1, total_size: int | None =
             raise
 
     if extract:
-        if not os.path.exists(extract_path):
+        if not os.path.exists(target_path):
             _extract(full_path, path_)
-        return extract_path
+        return target_path
 
     return full_path