Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
mikel-brostrom committed Jul 12, 2024
1 parent 14b1666 commit 0fd4f65
Showing 1 changed file with 22 additions and 4 deletions.
26 changes: 22 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -39,14 +39,14 @@ This repo contains a collections of pluggable state-of-the-art multi-object trac
</details>

<details>
<summary>Tutorials</summary>
<summary>3rd party resources</summary>

* [ROS wrapper for boxmot](https://github.com/KalanaRatnayake/boxmot_ros)&nbsp;
* [Yolov10 Integration with BoxMOT (link to external Notebook)](https://colab.research.google.com/drive/1-QV2TNfqaMsh14w5VxieEyanugVBG14V?usp=drive_link)&nbsp;
* [Yolov8 training (link to external repository)](https://docs.ultralytics.com/modes/train/)&nbsp;
* [Deep appearance descriptor training (link to external repository)](https://kaiyangzhou.github.io/deep-person-reid/user_guide.html)&nbsp;
* [ReID model export to ONNX, OpenVINO, TensorRT and TorchScript](https://github.com/mikel-brostrom/yolo_tracking/wiki/ReID-multi-framework-model-export)&nbsp;
* [ReID model training (link to external repository)](https://kaiyangzhou.github.io/deep-person-reid/user_guide.html)&nbsp;
* [Evaluation on custom tracking dataset](https://github.com/mikel-brostrom/yolo_tracking/wiki/How-to-evaluate-on-custom-tracking-dataset)&nbsp;
* [ReID inference acceleration with Nebullvm](https://colab.research.google.com/drive/1APUZ1ijCiQFBR9xD0gUvFUOC8yOJIvHm?usp=sharing)&nbsp;
* [ReID model inference acceleration with Nebullvm](https://colab.research.google.com/drive/1APUZ1ijCiQFBR9xD0gUvFUOC8yOJIvHm?usp=sharing)&nbsp;

</details>

Expand Down Expand Up @@ -238,6 +238,24 @@ The set of hyperparameters leading to the best HOTA result are written to the tr

</details>

<details>
<summary>Export</summary>

We support ReID model export to ONNX, OpenVINO, TorchScript and TensorRT

```bash
# export to ONNX
$ python3 boxmot/appearance/reid_export.py --include onnx --device cpu
# export to OpenVINO
$ python3 boxmot/appearance/reid_export.py --include openvino --device cpu
# export to TensorRT with dynamic input
$ python3 boxmot/appearance/reid_export.py --include engine --device 0 --dynamic
```

The set of hyperparameters leading to the best HOTA result are written to the tracker's config file.

</details>


## Custom tracking examples

Expand Down

0 comments on commit 0fd4f65

Please sign in to comment.