Documentation

usls is a Rust library integrated with ONNXRuntime that provides a collection of state-of-the-art models for Computer Vision and Vision-Language tasks, including:

• YOLO Models: YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9, YOLOv10, YOLOv11
• SAM Models: SAM, SAM2, MobileSAM, EdgeSAM, SAM-HQ, FastSAM
• Vision Models: RTDETR, RTMO, DB, SVTR, Depth-Anything-v1-v2, DINOv2, MODNet, Sapiens, DepthPro
• Vision-Language Models: CLIP, BLIP, GroundingDINO, YOLO-World, Florence2

cargo run -r --example yolo   # blip, clip, yolop, svtr, db, ...

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

  cargo add usls

  Or use a specific commit:

  [dependencies]
  usls = { git = "https://github.com/jamjamjon/usls", rev = "commit-sha" }

• Follow the pipeline

  • Build model with the provided models and Options
  • Load images, video and stream with DataLoader
  • Do inference
  • Retrieve inference results from Vec<Y>
  • Annotate inference results with Annotator
  • Display images and write them to video with Viewer
  
  
  example code

  use usls::{models::YOLO, Annotator, DataLoader, Nms, Options, Vision, YOLOTask, YOLOVersion};
  
  fn main() -> anyhow::Result<()> {
      // Build model with Options
      let options = Options::new()
          .with_trt(0)
          .with_model("yolo/v8-m-dyn.onnx")?
          .with_yolo_version(YOLOVersion::V8) // YOLOVersion: V5, V6, V7, V8, V9, V10, RTDETR
          .with_yolo_task(YOLOTask::Detect) // YOLOTask: Classify, Detect, Pose, Segment, Obb
          .with_ixx(0, 0, (1, 2, 4).into())
          .with_ixx(0, 2, (0, 640, 640).into())
          .with_ixx(0, 3, (0, 640, 640).into())
          .with_confs(&[0.2]);
      let mut model = YOLO::new(options)?;
  
      // Build DataLoader to load image(s), video, stream
      let dl = DataLoader::new(
          // "./assets/bus.jpg", // local image
          // "images/bus.jpg",  // remote image
          // "../images-folder",  // local images (from folder)
          // "../demo.mp4",  // local video
          // "http://commondatastorage.googleapis.com/gtv-videos-bucket/sample/BigBuckBunny.mp4",  // online video
          "rtsp://admin:kkasd1234@192.168.2.217:554/h264/ch1/",  // stream
      )?
      .with_batch(2)  // iterate with batch_size = 2
      .build()?;
  
      // Build annotator
      let annotator = Annotator::new()
          .with_bboxes_thickness(4)
          .with_saveout("YOLO-DataLoader");
  
      // Build viewer
      let mut viewer = Viewer::new().with_delay(10).with_scale(1.).resizable(true);
  
      // Run and annotate results
      for (xs, _) in dl {
          let ys = model.forward(&xs, false)?;
          // annotator.annotate(&xs, &ys);
          let images_plotted = annotator.plot(&xs, &ys, false)?;
  
          // show image
          viewer.imshow(&images_plotted)?;
  
          // check out window and key event
          if !viewer.is_open() || viewer.is_key_pressed(usls::Key::Escape) {
              break;
          }
  
          // write video
          viewer.write_batch(&images_plotted)?;
  
          // Retrieve inference results
          for y in ys {
              // bboxes
              if let Some(bboxes) = y.bboxes() {
                  for bbox in bboxes {
                      println!(
                          "Bbox: {}, {}, {}, {}, {}, {}",
                          bbox.xmin(),
                          bbox.ymin(),
                          bbox.xmax(),
                          bbox.ymax(),
                          bbox.confidence(),
                          bbox.id(),
                      );
                  }
              }
          }
      }
  
      // finish video write
      viewer.finish_write()?;
  
      Ok(())
  }

  
  

This project is licensed under LICENSE.