Update RKNN2 model card and supported chips
Browse files
README.md
CHANGED
|
@@ -3,13 +3,16 @@ license: apache-2.0
|
|
| 3 |
pipeline_tag: object-detection
|
| 4 |
tags:
|
| 5 |
- rknn
|
|
|
|
| 6 |
- rockchip
|
|
|
|
|
|
|
| 7 |
- yolox
|
| 8 |
---
|
| 9 |
|
| 10 |
-
# YOLOX
|
| 11 |
|
| 12 |
-
YOLOX Nano FP16 and INT8 models for RK3576 and RK3588. Download `model.rknn` and `metadata.yaml` from the same directory under `models/detect/yolox_nano/<chip>/<precision>/`. The [manifest](manifest.json) records each model hash.
|
| 13 |
|
| 14 |
The [original YOLOX Nano checkpoint](https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yolox_nano.pth) is included under [source](tree/main/source). It was exported to ONNX with the [Rockchip YOLOX exporter](https://github.com/airockchip/YOLOX/tree/fc69c1e2ccb30fce7e18250bddc13a68090dca09) and compiled with the [Model Zoo YOLOX converter](https://github.com/airockchip/rknn_model_zoo/tree/837db8e992815ff8647eadb709f07067f4bc3a71/examples/yolox) using RKNN Toolkit2 2.3.2. The conversion changed the model format and quantized the INT8 variant.
|
| 15 |
|
|
|
|
| 3 |
pipeline_tag: object-detection
|
| 4 |
tags:
|
| 5 |
- rknn
|
| 6 |
+
- rknn2
|
| 7 |
- rockchip
|
| 8 |
+
- rk3576
|
| 9 |
+
- rk3588
|
| 10 |
- yolox
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# YOLOX-Nano-RKNN2
|
| 14 |
|
| 15 |
+
Rockchip Model Zoo conversion of YOLOX Nano for RK3576 and RK3588. YOLOX Nano FP16 and INT8 models for RK3576 and RK3588. Download `model.rknn` and `metadata.yaml` from the same directory under `models/detect/yolox_nano/<chip>/<precision>/`. The [manifest](manifest.json) records each model hash.
|
| 16 |
|
| 17 |
The [original YOLOX Nano checkpoint](https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yolox_nano.pth) is included under [source](tree/main/source). It was exported to ONNX with the [Rockchip YOLOX exporter](https://github.com/airockchip/YOLOX/tree/fc69c1e2ccb30fce7e18250bddc13a68090dca09) and compiled with the [Model Zoo YOLOX converter](https://github.com/airockchip/rknn_model_zoo/tree/837db8e992815ff8647eadb709f07067f4bc3a71/examples/yolox) using RKNN Toolkit2 2.3.2. The conversion changed the model format and quantized the INT8 variant.
|
| 18 |
|