Update RKNN2 model card and supported chips
Browse files
README.md
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gpl-3.0
|
| 3 |
+
pipeline_tag: image-classification
|
| 4 |
+
tags:
|
| 5 |
+
- rknn
|
| 6 |
+
- rknn2
|
| 7 |
+
- rockchip
|
| 8 |
+
- rk3576
|
| 9 |
+
- rk3588
|
| 10 |
+
- yolov5
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# YOLOv5-Cls-RKNN2
|
| 14 |
+
|
| 15 |
+
Custom conversion in the Rockchip Model Zoo collection. YOLOv5 n, s and m classifiers in FP16 and INT8 for RK3576 and RK3588. Download the model and metadata from the same directory under `models/classify/<checkpoint>/<chip>/<precision>/`.
|
| 16 |
+
|
| 17 |
+
The original classification weights came from the [YOLOv5 v7.0 release](https://github.com/ultralytics/yolov5/releases/tag/v7.0) and are included with their hashes and original URLs in [source](tree/main/source). The distribution includes the [GPL-3.0 license](LICENSE) from that release.
|
| 18 |
+
|
| 19 |
+
The custom conversion exports an ONNX graph and compiles it with RKNN Toolkit2. See `source/convert-extended.py --help` and use the [v7.0 source checkout](https://github.com/ultralytics/yolov5/tree/v7.0) with `--yolov5-source`. INT8 uses the COCO128 calibration list in `source/calibration.json`. The [manifest](manifest.json) lists all output hashes.
|