API to run inferences with YoloV5 models. Written in Rust, based on OpenCV 4.5.5

If you need a C++ version, check my C++ Yolov5-API

• OpenCV 4.5.5 installed on your system
  • Follow Rust opencv README

Data directory must contain your config.json

config.json defines:

• ONNX absolute model path
• input size (640 default)
• array of class names

A dummy example is available in the data/ folder

docker run --name rust-yolov5-api -v <model data dir>:/app/data -p 5000:5000 mascit/rust-yolov5-api:latest

Development:

cargo build

Release:

cargo build --release

cargo run

For Windows users: Assure to have opencv_world455.dll in your exe directory.

• Image bytes (binary in Postman)

• X-Confidence-Thresh
  • default 0.5
• X-NMS-Thresh
  • default 0.45
• X-Return
  • image_with_boxes
    • A JPEG image with drawn predictions
  • json (default)
    • A json array containing predictions. Each object defines: xmin, ymin, xmax, ymax, conf, class_name