Add logger, tests and refactor

.github/workflows/tests.yaml

@@ -2,19 +2,23 @@ name: Tests
 
 on:
   pull_request:
-    branches: [ dev, main ]
+    branches: [ main ]
     paths:
       - 'datadreamer/**/**.py'
-      - 'tests/**/**.py'
+      - 'tests/core_tests/**/**.py'
       - .github/workflows/tests.yaml
+  workflow_dispatch:
 
 jobs:
   run_tests:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest, windows-latest, macOS-latest]
+        os: [buildjet-8vcpu-ubuntu-2204, windows-latest, macOS-latest]
         version: ['3.10', '3.11']
+        exclude:
+          - os: buildjet-8vcpu-ubuntu-2204
+            version: '3.11'
 
     runs-on: ${{ matrix.os }}
 
@@ -31,56 +35,52 @@ jobs:
         cache: pip
 
     - name: Install dependencies [Ubuntu]
-      if: matrix.os == 'ubuntu-latest'
+      if: matrix.os == 'buildjet-8vcpu-ubuntu-2204'
       run: |
         sudo apt update
         sudo apt install -y pandoc
         pip install -e .[dev]
         pip install coverage-badge>=1.1.0 pytest-cov>=4.1.0
-
     - name: Install dependencies [Windows]
       if: matrix.os == 'windows-latest'
       run: |
         pip install -e .[dev]
         pip install coverage-badge>=1.1.0 pytest-cov>=4.1.0
-
     - name: Install dependencies [macOS]
       if: matrix.os == 'macOS-latest'
       run: |
         pip install -e .[dev]
         pip install coverage-badge>=1.1.0 pytest-cov>=4.1.0
-
     - name: Run tests with coverage [Ubuntu]
-      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
-      run: pytest tests --cov=datadreamer --cov-report xml --junit-xml pytest.xml
+      if: matrix.os == 'buildjet-8vcpu-ubuntu-2204' && matrix.version == '3.10'
+      run: pytest tests/core_tests --cov=datadreamer --cov-report xml --junit-xml pytest.xml
 
     - name: Run tests [Windows, macOS]
-      if: matrix.os != 'ubuntu-latest' || matrix.version != '3.10'
-      run: pytest tests --junit-xml pytest.xml
+      if: matrix.os != 'buildjet-8vcpu-ubuntu-2204'
+      run: pytest tests/core_tests --junit-xml pytest.xml
 
     - name: Generate coverage badge [Ubuntu]
-      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
+      if: matrix.os == 'buildjet-8vcpu-ubuntu-2204' && matrix.version == '3.10'
       run: coverage-badge -o media/coverage_badge.svg -f
 
     - name: Generate coverage report [Ubuntu]
-      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
+      if: matrix.os == 'buildjet-8vcpu-ubuntu-2204' && matrix.version == '3.10'
       uses: orgoro/[email protected]
       with:
         coverageFile: coverage.xml
         token: ${{ secrets.GITHUB_TOKEN }}
 
     - name: Commit coverage badge [Ubuntu]
-      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
+      if: matrix.os == 'buildjet-8vcpu-ubuntu-2204' && matrix.version == '3.10'
       run: |
         git config --global user.name 'GitHub Actions'
         git config --global user.email '[email protected]'
         git diff --quiet media/coverage_badge.svg || {
           git add media/coverage_badge.svg
           git commit -m "[Automated] Updated coverage badge"
         }
-
     - name: Push changes [Ubuntu]
-      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
+      if: matrix.os == 'buildjet-8vcpu-ubuntu-2204' && matrix.version == '3.10'
       uses: ad-m/github-push-action@master
       with:
         branch: ${{ github.head_ref }}
@@ -117,4 +117,4 @@ jobs:
       - name: Publish Test Results
         uses: EnricoMi/publish-unit-test-result-action@v2
         with:
-          files: "artifacts/**/*.xml"
+          files: "artifacts/**/*.xml"

.github/workflows/unit-tests.yaml

@@ -0,0 +1,116 @@
+name: Unit tests
+
+on:
+  pull_request:
+    branches: [ dev ]
+    paths:
+      - 'datadreamer/**/**.py'
+      - 'tests/core_tests/unittests/**.py'
+      - .github/workflows/unit-tests.yaml
+
+jobs:
+  run_tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, windows-latest, macOS-latest]
+        version: ['3.10', '3.11']
+
+    runs-on: ${{ matrix.os }}
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        ref: ${{ github.head_ref }}
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.version }}
+        cache: pip
+
+    - name: Install dependencies [Ubuntu]
+      if: matrix.os == 'ubuntu-latest'
+      run: |
+        sudo apt update
+        sudo apt install -y pandoc
+        pip install -e .[dev]
+        pip install coverage-badge>=1.1.0 pytest-cov>=4.1.0
+    - name: Install dependencies [Windows]
+      if: matrix.os == 'windows-latest'
+      run: |
+        pip install -e .[dev]
+        pip install coverage-badge>=1.1.0 pytest-cov>=4.1.0
+    - name: Install dependencies [macOS]
+      if: matrix.os == 'macOS-latest'
+      run: |
+        pip install -e .[dev]
+        pip install coverage-badge>=1.1.0 pytest-cov>=4.1.0
+    - name: Run tests with coverage [Ubuntu]
+      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
+      run: pytest tests/core_tests/unittests --cov=datadreamer --cov-report xml --junit-xml pytest.xml
+
+    - name: Run tests [Windows, macOS]
+      if: matrix.os != 'ubuntu-latest' || matrix.version != '3.10'
+      run: pytest tests/core_tests/unittests --junit-xml pytest.xml
+
+    - name: Generate coverage badge [Ubuntu]
+      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
+      run: coverage-badge -o media/coverage_badge.svg -f
+
+    - name: Generate coverage report [Ubuntu]
+      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
+      uses: orgoro/[email protected]
+      with:
+        coverageFile: coverage.xml
+        token: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Commit coverage badge [Ubuntu]
+      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
+      run: |
+        git config --global user.name 'GitHub Actions'
+        git config --global user.email '[email protected]'
+        git diff --quiet media/coverage_badge.svg || {
+          git add media/coverage_badge.svg
+          git commit -m "[Automated] Updated coverage badge"
+        }
+    - name: Push changes [Ubuntu]
+      if: matrix.os == 'ubuntu-latest' && matrix.version == '3.10'
+      uses: ad-m/github-push-action@master
+      with:
+        branch: ${{ github.head_ref }}
+
+    - name: Upload Test Results
+      if: always()
+      uses: actions/upload-artifact@v4
+      with:
+        name: Test Results [${{ matrix.os }}] (Python ${{ matrix.version }})
+        path: pytest.xml
+        retention-days: 10
+        if-no-files-found: error
+
+  publish-test-results:
+    name: "Publish Tests Results"
+    needs: run_tests
+    runs-on: ubuntu-latest
+    permissions:
+      checks: write
+      pull-requests: write
+    if: always()
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+
+      - name: Download Artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: artifacts
+
+      - name: Publish Test Results
+        uses: EnricoMi/publish-unit-test-result-action@v2
+        with:
+          files: "artifacts/**/*.xml"

datadreamer/dataset_annotation/clip_annotator.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
-from typing import List
+import logging
+from typing import Dict, List
 
 import numpy as np
 import PIL
@@ -10,6 +11,8 @@
 
 from datadreamer.dataset_annotation.image_annotator import BaseAnnotator, TaskList
 
+logger = logging.getLogger(__name__)
+
 
 class CLIPAnnotator(BaseAnnotator):
     """A class for image annotation using the CLIP model, specializing in image
@@ -47,7 +50,7 @@ def __init__(
         self.device = device
         self.model.to(self.device)
 
-    def _init_processor(self):
+    def _init_processor(self) -> CLIPProcessor:
         """Initializes the CLIP processor.
 
         Returns:
@@ -57,12 +60,13 @@ def _init_processor(self):
             return CLIPProcessor.from_pretrained("openai/clip-vit-large-patch14")
         return CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
-    def _init_model(self):
+    def _init_model(self) -> CLIPModel:
         """Initializes the CLIP model.
 
         Returns:
             CLIPModel: The initialized CLIP model.
         """
+        logger.info(f"Initializing CLIP {self.size} model...")
         if self.size == "large":
             return CLIPModel.from_pretrained("openai/clip-vit-large-patch14")
         return CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
@@ -72,7 +76,7 @@ def annotate_batch(
         images: List[PIL.Image.Image],
         objects: List[str],
         conf_threshold: float = 0.1,
-        synonym_dict: dict[str, List[str]] | None = None,
+        synonym_dict: Dict[str, List[str]] | None = None,
     ) -> List[np.ndarray]:
         """Annotates images using the OWLv2 model.
 
@@ -83,7 +87,7 @@ def annotate_batch(
             synonym_dict (dict, optional): Dictionary for handling synonyms in labels. Defaults to None.
 
         Returns:
-            List[List[int]]: A list of lists of labels for each image.
+            List[np.ndarray]: A list of the annotations for each image.
         """
         if synonym_dict is not None:
             objs_syn = set()

datadreamer/dataset_annotation/image_annotator.py

@@ -4,15 +4,12 @@
 from abc import ABC, abstractmethod
 
 
-# Enum for different labeling tasks
 class TaskList(enum.Enum):
     CLASSIFICATION = "classification"
     OBJECT_DETECTION = "object_detection"
     SEGMENTATION = "segmentation"
-    # Add more tasks as needed
 
 
-# Abstract base class for data labeling
 class BaseAnnotator(ABC):
     """Abstract base class for creating annotators.
 
@@ -24,6 +21,8 @@ class BaseAnnotator(ABC):
     Methods:
         annotate_batch(): Abstract method to be implemented by subclasses. It should contain
                     the logic for performing annotation based on the task definition.
+        release(): Abstract method to be implemented by subclasses. It should contain
+                    the logic for releasing the resources used by the annotator.
     """
 
     def __init__(
@@ -35,3 +34,7 @@ def __init__(
     @abstractmethod
     def annotate_batch(self):
         pass
+
+    @abstractmethod
+    def release(self, empty_cuda_cache=False) -> None:
+        pass