metadata
license: other
license_name: upstream-terms-by-artifact
license_link: https://huggingface.co/HanzoHuang/YOLOX-RKNN2/blob/main/LICENSES.md
pipeline_tag: object-detection
tags:
- rknn
- rknn2
- rockchip
- rk3576
- rk3588
- yolox
YOLOX-RKNN2
Looking for Ultralytics RKNN exports? Browse the Ultralytics exports collection.
Rockchip Model Zoo conversions of YOLOX Nano for RK3576 and RK3588, with FP16 and INT8 variants.
Choose a model
For Toolkit 2.5.0, select a directory under models/v2.5.0/detect/yolox_nano/<chip>/<precision>/ and download model.rknn and metadata.yaml together. The manifest records model hashes.
- Toolkit 2.5.0 builds use RKNN Toolkit2 2.5.0. Conversion receipts identify the original ONNX model and converter.
- Toolkit 2.3.2 builds were tested on their target board. Each receipt identifies its source graph and compiler.
Conversion and license
The original YOLOX Nano checkpoint is included in source. It was exported to ONNX with the Rockchip YOLOX exporter and compiled with the Model Zoo YOLOX converter and RKNN Toolkit2 2.5.0. The INT8 variant was quantized during conversion.
YOLOX is from Megvii-BaseDetection. See LICENSE and source and license notices for the applicable terms.