feat: RND-116: YOLOv8 ML Backend

.github/workflows/gitleaks.yml

@@ -0,0 +1,57 @@
+name: "Gitleaks"
+
+on:
+  pull_request:
+
+env:
+  GIT_GITLEAKS_VERSION: 8.18.4
+  ACTIONS_STEP_DEBUG: '${{ secrets.ACTIONS_STEP_DEBUG }}'
+
+jobs:
+  gitleaks:
+    name: "Gitleaks"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: hmarr/[email protected]
+
+      - name: Configure gitleaks binary cache
+        id: cache
+        uses: actions/cache@v4
+        with:
+          path: /usr/local/bin/gitleaks
+          key: gitleaks-${{ env.GIT_GITLEAKS_VERSION }}
+
+      - name: Install tools
+        if: steps.cache.outputs.cache-hit != 'true'
+        run: |
+          wget -O - \
+          "https://github.com/zricethezav/gitleaks/releases/download/v${{ env.GIT_GITLEAKS_VERSION }}/gitleaks_${{ env.GIT_GITLEAKS_VERSION }}_linux_x64.tar.gz" \
+            | sudo tar xzf - -C /usr/local/bin
+
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.sha || github.event.after }}
+
+      - name: Run gitleaks
+        run: |
+          set -euo pipefail ${ACTIONS_STEP_DEBUG:+-x}
+
+          gitleaks \
+            detect \
+            --source="." \
+            --redact \
+            -v \
+            --exit-code=2 \
+            --report-format=sarif \
+            --report-path=results.sarif \
+            --log-level=debug \
+            --log-opts='${{ github.event.pull_request.base.sha || github.event.before }}..${{ github.event.pull_request.head.sha || github.event.after }}'
+
+      - name: Upload test results
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: GitLeaks results
+          path: results.sarif

README.md

@@ -61,6 +61,8 @@ Check the **Required parameters** column to see if you need to set any additiona
 | [spacy](/label_studio_ml/examples/spacy)                                                   | NER by [SpaCy](https://spacy.io/)                                                                                                                    | ✅              | ❌                | ❌        | None                       | Set      [(see documentation)](https://spacy.io/usage/linguistic-features) |
 | [tesseract](/label_studio_ml/examples/tesseract)                                           | Interactive OCR. [Details](https://github.com/tesseract-ocr/tesseract)                                                                               | ❌              | ✅                | ❌        | None                       | Set (characters)                                                           | 
 | [watsonX](/label_studio_ml/exampels/watsonx)| LLM inference with [WatsonX](https://www.ibm.com/products/watsonx-ai) and integration with [WatsonX.data](watsonx.data)| ✅ | ✅| ❌ | None| Arbitrary|
+| [yolo](/label_studio_ml/examples/yolo)                                                     | Object detection with [YOLO](https://docs.ultralytics.com/tasks/) | ✅ | ❌ | ❌ | None | Arbitrary |
+
 # (Advanced usage) Develop your model
 
 To start developing your own ML backend, follow the instructions below.

label_studio_ml/examples/grounding_dino/README.md

@@ -40,7 +40,7 @@ See [here](https://github.com/IDEA-Research/GroundingDINO) for more details abou
 
     Example:
    - `LABEL_STUDIO_HOST=http://123.456.7.8:8080`
-   - `LABEL_STUDIO_ACCESS_TOKEN=c9djf998eii2948ee9hh835nferkj959923`
+   - `LABEL_STUDIO_ACCESS_TOKEN=your-api-key`
 
 3. Run `docker compose up`
 4. Check the IP of your backend using `docker ps`. You will use this URL when connecting the backend to a Label Studio project. Usually this is `http://localhost:9090`.

label_studio_ml/examples/grounding_sam/README.md

@@ -43,7 +43,7 @@ See [here](https://github.com/IDEA-Research/GroundingDINO) for more details abou
 
     Example:
    - `LABEL_STUDIO_HOST=http://123.456.7.8:8080`
-   - `LABEL_STUDIO_ACCESS_TOKEN=c9djf998eii2948ee9hh835nferkj959923`
+   - `LABEL_STUDIO_ACCESS_TOKEN=your-api-key`
 
 3. Run `docker compose up`
 4. Check the IP of your backend using `docker ps`. You will use this URL when connecting the backend to a Label Studio project. Usually this is `http://localhost:9090`.

label_studio_ml/examples/grounding_sam/docker-compose.yml

@@ -3,7 +3,7 @@ version: "3.11"
 services:
   grounding_sam:
     container_name: grounding_sam
-    image: heartexlabs/label-studio-ml-backend:grndsam-master
+    image: heartexlabs/label-studio-ml-backend:grounding_sam-master
     build:
       context: .
       args:

label_studio_ml/examples/mmdetection-3/mmdetection.py

@@ -100,6 +100,7 @@ def build_labels_from_labeling_config(self, schema):
             for ls_label, label_attrs in self.labels_attrs.items():
                 predicted_values = label_attrs.get("predicted_values", "").split(",")
                 for predicted_value in predicted_values:
+                    predicted_value = predicted_value.strip()  # remove spaces at the beginning and at the end
                     if predicted_value:  # it shouldn't be empty (like '')
                         if predicted_value not in mmdet_labels:
                             print(

label_studio_ml/examples/mmdetection-3/requirements-base.txt

@@ -1,2 +1,2 @@
 gunicorn==22.0.0
-label-studio-ml @ git+https://github.com/HumanSignal/label-studio-ml-backend.git
+label-studio-ml @ git+https://github.com/HumanSignal/label-studio-ml-backend.git@fix/rnd-117

label_studio_ml/examples/mmdetection-3/test_model.py

@@ -2,7 +2,7 @@
 
 from mmdetection import MMDetection
 
-from pytest import approx
+from label_studio_ml.utils import compare_nested_structures
 
 label_config = """
 <View>
@@ -41,22 +41,6 @@
 ]
 
 
-def compare_nested_structures(a, b, path=""):
-    """Compare two dicts or list with approx() for float values"""
-    if isinstance(a, dict) and isinstance(b, dict):
-        assert a.keys() == b.keys(), f"Keys mismatch at {path}"
-        for key in a.keys():
-            compare_nested_structures(a[key], b[key], path + "." + str(key))
-    elif isinstance(a, list) and isinstance(b, list):
-        assert len(a) == len(b), f"List size mismatch at {path}"
-        for i, (act_item, exp_item) in enumerate(zip(a, b)):
-            compare_nested_structures(act_item, exp_item, path + f"[{i}]")
-    elif isinstance(a, float) and isinstance(b, float):
-        assert a == approx(b), f"Mismatch at {path}"
-    else:
-        assert a == b, f"Mismatch at {path}"
-
-
 def test_mmdetection_model_predict():
     model = MMDetection(label_config=label_config)
     predictions = model.predict([task])

label_studio_ml/examples/yolo/.dockerignore

@@ -0,0 +1,22 @@
+# Exclude everything
+**
+
+# Include Dockerfile and docker-compose for reference (optional, decide based on your use case)
+!Dockerfile
+!docker-compose.yml
+
+# Include Python application files
+!*.py
+!*.yaml
+!tests/*
+!control_models/*
+!models/*
+
+# Include requirements files
+!requirements*.txt
+
+# Include script
+!*.sh
+
+# Exclude specific requirements if necessary
+# requirements-test.txt (Uncomment if you decide to exclude this)

label_studio_ml/examples/yolo/Dockerfile

@@ -0,0 +1,62 @@
+FROM pytorch/pytorch:2.1.2-cuda12.1-cudnn8-runtime
+ARG DEBIAN_FRONTEND=noninteractive
+ARG TEST_ENV
+
+WORKDIR /app
+
+RUN conda update conda -y
+
+RUN --mount=type=cache,target="/var/cache/apt",sharing=locked \
+    --mount=type=cache,target="/var/lib/apt/lists",sharing=locked \
+    apt-get -y update \
+    && apt-get install -y git \
+    && apt-get install -y wget \
+    && apt-get install -y g++ freeglut3-dev build-essential libx11-dev \
+    libxmu-dev libxi-dev libglu1-mesa libglu1-mesa-dev libfreeimage-dev \
+    && apt-get -y install ffmpeg libsm6 libxext6 libffi-dev python3-dev python3-pip gcc
+
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PIP_CACHE_DIR=/.cache \
+    PORT=9090 \
+    WORKERS=2 \
+    THREADS=4 \
+    CUDA_HOME=/usr/local/cuda
+
+RUN conda install -c "nvidia/label/cuda-12.1.1" cuda -y
+ENV CUDA_HOME=/opt/conda \
+    TORCH_CUDA_ARCH_LIST="6.0;6.1;7.0;7.5;8.0;8.6+PTX;8.9;9.0"
+
+# install base requirements
+COPY requirements-base.txt .
+RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+    pip install -r requirements-base.txt
+
+# install model requirements
+COPY requirements.txt .
+RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+    pip3 install -r requirements.txt
+
+# install test requirements if needed
+COPY requirements-test.txt .
+# build only when TEST_ENV="true"
+RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+    if [ "$TEST_ENV" = "true" ]; then \
+      pip3 install -r requirements-test.txt; \
+    fi
+
+WORKDIR /app
+
+COPY . ./
+
+WORKDIR /app/models
+
+# Download the YOLO models
+RUN yolo predict model=yolov8m.pt source=/app/tests/car.jpg \
+    && yolo predict model=yolov8n.pt source=/app/tests/car.jpg \
+    && yolo predict model=yolov8n-cls.pt source=/app/tests/car.jpg \
+    && yolo predict model=yolov8n-seg.pt source=/app/tests/car.jpg
+
+WORKDIR /app
+
+CMD ["/app/start.sh"]