flystem-usls/examples/yolo-world
Jamjamjon a5141a53be
Accelerate model pre-processing and post-processing (#23)
* Add X struct to handle input and preprocessing

*Add Ops struct to manage common operations

* Use SIMD (fast_image_resize) to accelerate model pre-processing and post-processing
2024-06-30 15:19:34 +08:00
..
README.md Add YOLOv8-OBB and some bug fixes (#9) 2024-04-21 17:06:58 +08:00
demo.png Add YOLOv8-OBB and some bug fixes (#9) 2024-04-21 17:06:58 +08:00
main.rs Accelerate model pre-processing and post-processing (#23) 2024-06-30 15:19:34 +08:00

README.md

Quick Start

cargo run -r --example yolo-world

Donwload or Export ONNX Model

  • Download

    yolov8s-world-v2-shoes

  • Or generate your own yolo-world model 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
    

Results