| license: agpl-3.0 | |
| tags: | |
| - rknn | |
| - rknn2 | |
| - rockchip | |
| - rk3576 | |
| - rk3588 | |
| # YOLOv10-RKNN2 | |
| > **Looking for the Ultralytics RKNN exports?** See [YOLOv10-RKNN2-Ultralytics](https://huggingface.co/HanzoHuang/YOLOv10-RKNN2-Ultralytics). | |
| YOLOv10 RKNN exports for **RK3576** and **RK3588**, compiled with RKNN Toolkit2 2.3.2. Available tasks: detection. | |
| ## Choose a model | |
| Models are organized by toolkit version, task, variant, target chip, and precision: | |
| ```text | |
| models/v<toolkit-version>/<task>/<variant>/<chip>/<precision>/ | |
| ``` | |
| Download `model.rknn` and `metadata.yaml` from the same directory. The [manifest](manifest.json) lists the available models and checksums. | |
| ## Conversion | |
| Detection models were converted on Seeed-Dev with RKNN Toolkit2 2.3.2 using ONNX inputs supplied by the Rockchip Model Zoo. The [manifest](manifest.json) records input ONNX and output RKNN checksums. The ONNX graphs and Model Zoo download URLs are in [source/onnx](tree/main/source/onnx); the graphs declare their Ultralytics exporter versions and AGPL-3.0 license. | |
| ## Source and license | |
| Original checkpoints, conversion scripts, and provenance are in [source](tree/main/source). The models and checkpoints are distributed under AGPL-3.0; see [LICENSE](LICENSE) and [checkpoint details](source/weights.json). | |