usls

A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models including YOLOv8 (Classification, Segmentation, Detection and Pose Detection), YOLOv9, RTDETR, CLIP, DINOv2, FastSAM, YOLO-World, BLIP, and others. Many execution providers are supported, sunch as CUDA, TensorRT and CoreML.

Supported Models

Solution Models

Additionally, this repo also provides some solution models such as pedestrian fall detection, head detection, trash detection, and more.

Demo

cargo run -r --example yolov8   # fastsam, yolov9, blip, clip, dinov2, yolo-world...

Integrate into your own project

1. Install ort

check ort guide

• Firstly, download from latest release from ONNXRuntime Releases
• Then linking

  export ORT_DYLIB_PATH=/Users/qweasd/Desktop/onnxruntime-osx-arm64-1.17.1/lib/libonnxruntime.1.17.1.dylib
  

2. Add usls as a dependency to your project's Cargo.toml:

[dependencies]
usls = "0.0.1"

3. Set model Options and build model, then you're ready to go.

2use usls::{models::YOLO, Options};

fn main() -> Result<(), Box<dyn std::error::Error>> {
    // 1.build model
    let options = Options::default()
        .with_model("../models/yolov8m-seg-dyn-f16.onnx")
        .with_trt(0) // using cuda(0) by default
	// when model with dynamic shapes
        .with_i00((1, 2, 4).into()) // dynamic batch
        .with_i02((416, 640, 800).into())   // dynamic height
        .with_i03((416, 640, 800).into())   // dynamic width
        .with_confs(&[0.4, 0.15]) // person: 0.4, others: 0.15
        .with_saveout("YOLOv8");    // save results
    let mut model = YOLO::new(&options)?;

    // 2.build dataloader
    let dl = DataLoader::default()
        .with_batch(model.batch.opt as usize)
        .load("./assets/")?;

    // 3.run
    for (xs, _paths) in dl {
        let _y = model.run(&xs)?;
    }
    Ok(())
}

Script: converte ONNX model from float32 to float16

import onnx
from pathlib import Path
from onnxconverter_common import float16

model_f32 = "onnx_model.onnx"
model_f16 = float16.convert_float_to_float16(onnx.load(model_f32))
saveout = Path(model_f32).with_name(Path(model_f32).stem + "-f16.onnx")
onnx.save(model_f16, saveout)