diff --git a/cpp/rknn/README.md b/cpp/rknn/README.md index b793dcd..df3728c 100644 --- a/cpp/rknn/README.md +++ b/cpp/rknn/README.md @@ -4,8 +4,8 @@ | Model | Size | FPSRK3588, 3 cores
int8 batch=1
include all process | Download | |:------|:---------:|:-----------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| -|**Tiny-LRELU**| 384×640 | 55 | [**model**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_lrelu_coco.rknn), [**config**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_lrelu_coco.yaml) | -|**Tiny** | 384×640 | 22
(too many SiLU activate layers) | [**model**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_coco.rknn), [**config**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_coco.yaml) | +|**Tiny-LRELU**| 384×640 | 55 | [**coco model**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_lrelu_coco.rknn), [**coco config**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_lrelu_coco.yaml)
[**visdrone model**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_lrelu_visdrone.rknn), [**visdrone config**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_lrelu_visdrone.yaml) | +|**Tiny** | 384×640 | 22
(too many SiLU activate layers) | [**coco model**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_coco.rknn), [**coco config**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_coco.yaml)
[**visdrone model**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_visdrone.rknn), [**visdrone config**](https://github.com/LSH9832/edgeyolo/releases/download/v1.0.2/edgeyolo_tiny_visdrone.yaml) | ## 1. Model convert ### 1.1 Setup RKNN Toolkit2 on your PC(x86_64) with edgeyolo requirements