DataDreamer - v0.2.0

.github/workflows/gar-publish-dev.yaml

@@ -16,6 +16,8 @@ jobs:
     steps:
       - name: 'Checkout GitHub Action'
         uses: actions/checkout@main
+        with:
+          ref: dev  # Checkout the dev branch
 
       - id: 'auth'
         name: 'Authenticate to Google Cloud'
@@ -34,5 +36,5 @@ jobs:
       - name: 'Build Inventory Image'
         working-directory: .
         run: |
-          docker build --build-arg GITHUB_TOKEN=${{secrets.GHCR_PAT}} . --tag $GAR_LOCATION-docker.pkg.dev/$PROJECT_ID/internal/datadreamer:dev
-          docker push $GAR_LOCATION-docker.pkg.dev/$PROJECT_ID/internal/datadreamer --all-tags
+          docker build --build-arg GITHUB_TOKEN=${{secrets.GHCR_PAT}} --build-arg BRANCH=dev . --tag $GAR_LOCATION-docker.pkg.dev/$PROJECT_ID/internal/datadreamer:dev
+          docker push $GAR_LOCATION-docker.pkg.dev/$PROJECT_ID/internal/datadreamer --all-tags

.github/workflows/gar-publish.yaml

@@ -4,8 +4,6 @@ name: Deploy single image to GAR (Google Artifact Registry)
 
 on:
   workflow_dispatch:
-  release:
-    types: [published]
 env:
   PROJECT_ID: easyml-394818
   GAR_LOCATION: us-central1

.github/workflows/ghcr-publish-manual.yaml

@@ -0,0 +1,41 @@
+name: Manually deploy image to GHCR
+
+on:
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch to deploy'
+        required: true
+        default: 'dev'
+
+env:
+  GHCR_REGISTRY: ghcr.io
+  IMAGE_NAME: datadreamer
+
+jobs:
+  push-store:
+    name: Push the image to GHCR
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: 'Checkout GitHub Action'
+        uses: actions/checkout@v2
+        with:
+          ref: ${{ inputs.branch }}  # Checkout the selected branch
+
+      - name: 'Extract short commit hash'
+        id: commit_hash
+        run: echo "short_hash=$(git rev-parse --short HEAD)" >> $GITHUB_ENV
+
+      - name: Docker login to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: luxonis-ml
+          password: ${{ secrets.GHCR_PAT }}
+
+      - name: 'Build and Push Image to GHCR'
+        run: |
+          docker build --build-arg GITHUB_TOKEN=${{secrets.GHCR_PAT}} --build-arg BRANCH=${{ inputs.branch }} . \
+            --tag ghcr.io/luxonis/datadreamer:${{ steps.commit_hash.outputs.short_hash }}
+          docker push ghcr.io/luxonis/datadreamer --all-tags

.github/workflows/ghcr-publish.yaml

@@ -1,4 +1,4 @@
-name: Docker Build and Publish
+name: Deploy latest image to GHCR on release
 
 on:
   workflow_dispatch:

.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"

Dockerfile

@@ -7,9 +7,14 @@ WORKDIR /app
 ## instal
 RUN apt-get update && apt-get install ffmpeg libsm6 libxext6 -y
 RUN apt-get install -y git
-RUN git clone https://github.com/luxonis/datadreamer.git -b main
+
+## Define a build argument for the branch, defaulting to "main"
+ARG BRANCH=main
+
+## Clone the repository with the specified branch
+RUN git clone --branch ${BRANCH} https://github.com/luxonis/datadreamer.git
 
 RUN cd datadreamer && pip install .
 
 ## define image execution
-ENTRYPOINT ["datadreamer"]
+ENTRYPOINT ["datadreamer"]

README.md

@@ -157,13 +157,13 @@ datadreamer --config <path-to-config>
 
 ### 🔧 Additional Parameters
 
-- `--task`: Choose between detection and classification. Default is `detection`.
+- `--task`: Choose between detection, classification and instance segmentation. Default is `detection`.
 - `--dataset_format`: Format of the dataset. Defaults to `raw`. Supported values: `raw`, `yolo`, `coco`, `luxonis-dataset`, `cls-single`.
 - `--split_ratios`: Split ratios for train, validation, and test sets. Defaults to `[0.8, 0.1, 0.1]`.
 - `--num_objects_range`: Range of objects in a prompt. Default is 1 to 3.
-- `--prompt_generator`: Choose between `simple`, `lm` (language model) and `tiny` (tiny LM). Default is `simple`.
+- `--prompt_generator`: Choose between `simple`, `lm` (Mistral-7B), `tiny` (tiny LM), and `qwen2` (Qwen2.5 LM). Default is `qwen2`.
 - `--image_generator`: Choose image generator, e.g., `sdxl`, `sdxl-turbo` or `sdxl-lightning`. Default is `sdxl-turbo`.
-- `--image_annotator`: Specify the image annotator, like `owlv2` for object detection or `clip` for image classification. Default is `owlv2`.
+- `--image_annotator`: Specify the image annotator, like `owlv2` for object detection or `clip` for image classification or `owlv2-slimsam` for instance segmentation. Default is `owlv2`.
 - `--conf_threshold`: Confidence threshold for annotation. Default is `0.15`.
 - `--annotation_iou_threshold`: Intersection over Union (IoU) threshold for annotation. Default is `0.2`.
 - `--prompt_prefix`: Prefix to add to every image generation prompt. Default is `""`.
@@ -175,6 +175,7 @@ datadreamer --config <path-to-config>
 - `--image_tester_patience`: Patience level for image tester. Default is `1`.
 - `--lm_quantization`: Quantization to use for Mistral language model. Choose between `none` and `4bit`. Default is `none`.
 - `--annotator_size`: Size of the annotator model to use. Choose between `base` and `large`. Default is `base`.
+- `--disable_lm_filter`: Use only a bad word list for profanity filtering. Default is `False`.
 - `--batch_size_prompt`: Batch size for prompt generation. Default is 64.
 - `--batch_size_annotation`: Batch size for annotation. Default is `1`.
 - `--batch_size_image`: Batch size for image generation. Default is `1`.
@@ -190,12 +191,15 @@ datadreamer --config <path-to-config>
 | ----------------- | ------------------------------------------------------------------------------------- | --------------------------------------- |
 | Prompt Generation | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | Semantically rich prompts               |
 |                   | [TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) | Tiny LM                                 |
+|                   | [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)            | Qwen2.5 LM                              |
 |                   | Simple random generator                                                               | Joins randomly chosen object names      |
+| Profanity Filter  | [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)            | Fast and accurate LM profanity filter   |
 | Image Generation  | [SDXL-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)           | Slow and accurate (1024x1024 images)    |
 |                   | [SDXL-Turbo](https://huggingface.co/stabilityai/sdxl-turbo)                           | Fast and less accurate (512x512 images) |
 |                   | [SDXL-Lightning](https://huggingface.co/ByteDance/SDXL-Lightning)                     | Fast and accurate (1024x1024 images)    |
 | Image Annotation  | [OWLv2](https://huggingface.co/google/owlv2-base-patch16-ensemble)                    | Open-Vocabulary object detector         |
 |                   | [CLIP](https://huggingface.co/openai/clip-vit-base-patch32)                           | Zero-shot-image-classification          |
+|                   | [SlimSAM](https://huggingface.co/Zigeng/SlimSAM-uniform-50)                           | Zero-shot-instance-segmentation         |
 
 <a name="example"></a>
 
@@ -268,6 +272,23 @@ save_dir/
 }
 ```
 
+3. Instance Segmentation Annotations (instance_segmentation_annotations.json):
+
+- Each entry corresponds to an image and contains bounding boxes, masks and labels for objects in the image.
+- Format:
+
+```bash
+{
+  "image_path": {
+    "boxes": [[x_min, y_min, x_max, y_max], ...],
+    "masks": [[[x0, y0],[x1, y1],...], [[x0, y0],[x1, y1],...], ....]
+    "labels": [label_index, ...]
+  },
+  ...
+  "class_names": ["class1", "class2", ...]
+}
+```
+
 <a name="limitations"></a>
 
 ## ⚠️ Limitations
@@ -292,7 +313,7 @@ The above license does not cover the models. Please see the license of each mode
 
 ## 🙏 Acknowledgements
 
-This library was made possible by the use of several open-source projects, including Transformers, Diffusers, and others listed in the requirements.txt.
+This library was made possible by the use of several open-source projects, including Transformers, Diffusers, and others listed in the requirements.txt. Furthermore, we utilized a bad words list from [`@coffeeandfun/google-profanity-words`](https://github.com/coffee-and-fun/google-profanity-words) Node.js module created by Robert James Gabriel from Coffee & Fun LLC.
 
 [SD-XL 1.0 License](https://github.com/Stability-AI/generative-models/blob/main/model_licenses/LICENSE-SDXL1.0)
 [SDXL-Turbo License](https://github.com/Stability-AI/generative-models/blob/main/model_licenses/LICENSE-SDXL-Turbo)

datadreamer/dataset_annotation/__init__.py

@@ -3,5 +3,12 @@
 from .clip_annotator import CLIPAnnotator
 from .image_annotator import BaseAnnotator, TaskList
 from .owlv2_annotator import OWLv2Annotator
+from .slimsam_annotator import SlimSAMAnnotator
 
-__all__ = ["BaseAnnotator", "TaskList", "OWLv2Annotator", "CLIPAnnotator"]
+__all__ = [
+    "BaseAnnotator",
+    "TaskList",
+    "OWLv2Annotator",
+    "CLIPAnnotator",
+    "SlimSAMAnnotator",
+]