# YOLOv3 ONNX Conversion

## Prerequisites

### 1. Model files (cfg + weights)

The Darknet `.cfg` file is already provided in [opencv_extra/testdata/dnn](https://github.com/opencv/opencv_extra/tree/master/testdata/dnn) (`yolov3.cfg`).

Download the `.weights` file using the OpenCV test data download script:

```bash
git clone https://github.com/opencv/opencv_extra.git
cd opencv_extra/testdata/dnn
python download_models.py YOLOv3
```

### 2. Python environment for `pytorch-YOLOv4`

The conversion uses [`pytorch-YOLOv4`](https://github.com/Tianxiaomo/pytorch-YOLOv4). Create a Python environment with the required dependencies:

Supported Python versions: **3.8 – 3.10**.

```bash
conda create -n <env_name> python=<3.8-3.10> -y
conda activate <env_name>
pip install "torch<2.4" "torchvision<0.19" "numpy<2" onnx onnxruntime "onnxscript==0.1.0"
```

---

## Conversion of YOLOv3 to ONNX

### Why it requires a patch

The original YOLOv3 `.cfg` does not contain the `scale_x_y` field (introduced in YOLOv4). The `pytorch-YOLOv4` converter requires this field unconditionally, causing a `KeyError` when converting YOLOv3. The fix is to default `scale_x_y` to `1.0` when the field is absent.

### The Fix (modified script provided)

A patched version of **`darknet2pytorch.py`** is provided in this repository. It adds a default value for `scale_x_y` when the field is absent:

```python
# changed line in tool/darknet2pytorch.py
yolo_layer.scale_x_y = float(block.get('scale_x_y', 1.0))
```

### Conversion Steps

```bash
git clone https://github.com/Tianxiaomo/pytorch-YOLOv4.git
cd pytorch-YOLOv4

# [!] Replace tool/darknet2pytorch.py with the patched version from this repository
#     before running the conversion.

# Convert YOLOv3 (dynamic batch, batch_size=0)
python -c "from tool.darknet2onnx import transform_to_onnx; transform_to_onnx('yolov3.cfg', 'yolov3.weights', 0)"
```

The output file will be named `yolov4_-1_3_416_416_dynamic.onnx` (the script uses `yolov4` as the default prefix regardless of input model).

---

## Usage

A demo script is provided to run inference using OpenCV DNN:

```bash
python demo.py --model yolov3.onnx \
               --image example_outputs/input.jpg \
               --output example_outputs/yolov3_output.jpg
```

The demo prints the detected COCO classes, confidence scores, and bounding boxes, and saves an annotated output image.

---

## License

See [LICENSE](./LICENSE) — This conversion tool is based on [pytorch-YOLOv4](https://github.com/Tianxiaomo/pytorch-YOLOv4) (Apache-2.0). Original YOLOv3 model weights and configuration are released by Joseph Redmon ([pjreddie/darknet](https://github.com/pjreddie/darknet)).