* Update imageproc crates * Add top-p method for sampling * Add SVTR for text recognition & bug fix |
||
|---|---|---|
| .. | ||
| README.md | ||
| demo.jpg | ||
| main.rs | ||
README.md
Quick Start
cargo run -r --example yolo-world
Or you can manully
1. Donwload or Export ONNX Model
-
Download
-
Or generate your own
yolo-worldmodel and then Export- Installation
pip install -U ultralytics- Generate
from ultralytics import YOLO # Initialize a YOLO-World model model = YOLO('yolov8m-worldv2.pt') # Define custom classes model.set_classes(["shoes"]) # Save the model with the defined offline vocabulary model.save("custom_yolov8m-world-v2.pt")- Export
yolo export model=custom_yolov8m-world-v2.pt format=onnx simplify dynamic
2. Specify the ONNX model path in main.rs
let options = Options::default()
.with_model("ONNX_PATH"); // <= modify this
3. Then, run
cargo run -r --example yolo-world
