From 2ca0f48564289c8745ad3d2849e586f859cd526d Mon Sep 17 00:00:00 2001 From: RangiLyu Date: Sun, 11 Apr 2021 23:58:26 +0800 Subject: [PATCH] update download link --- README.md | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index 83cb85c8d..84edcc202 100644 --- a/README.md +++ b/README.md @@ -20,8 +20,7 @@ * [2021.02.03] Support [EfficientNet-Lite](https://github.com/RangiLyu/EfficientNet-Lite) and [Rep-VGG](https://github.com/DingXiaoH/RepVGG) backbone. Please check the [config folder](config/). Download models in [Model Zoo](#model-zoo) * [2021.01.10] **NanoDet-g** with lower memory access cost, which designed for edge NPU or GPU, is now available! - Check [config/nanodet-g.yml](config/nanodet-g.yml) and download: - [COCO pre-trained model(Google Drive)](https://drive.google.com/file/d/10uW7oqZKw231l_tr4C1bJWkbCXgBf7av/view?usp=sharing) | [(BaiduDisk百度网盘)](https://pan.baidu.com/s/1IJLdtLBvmQVOmzzNY_Ci5A) code:otcd + Check [config/nanodet-g.yml](config/nanodet-g.yml) and download in [Model Zoo](#model-zoo).
More... @@ -93,9 +92,8 @@ Inference using [Alibaba's MNN framework](https://github.com/alibaba/MNN) is in ### Pytorch demo First, install requirements and setup NanoDet following installation guide. Then download COCO pretrain weight from here -👉[COCO pretrain weight for torch>=1.6(Google Drive)](https://drive.google.com/file/d/1EhMqGozKfqEfw8y9ftbi1jhYu86XoW62/view?usp=sharing) | [(百度网盘)](https://pan.baidu.com/s/1LCnmj2Pqhv0tsDX__1j2gg) code:6au1 -👉[COCO pretrain weight for torch<=1.5(Google Drive)](https://drive.google.com/file/d/10h-0qLMCgYvWQvKULqbkLvmirFR-w9NN/view?usp=sharing) | [(百度云盘)](https://pan.baidu.com/s/1OTcPiajCcqKLg3Q0vwho3A) code:topw +👉[COCO pretrain weight (Google Drive)](https://drive.google.com/file/d/1ZkYucuLusJrCb_i63Lid0kYyyLvEiGN3/view?usp=sharing) * Inference images @@ -166,14 +164,14 @@ NanoDet supports variety of backbones. Go to the [***config*** folder](config/) Model | Backbone |Resolution|COCO mAP| FLOPS |Params | Pre-train weight | :--------------------:|:------------------:|:--------:|:------:|:-----:|:-----:|:-----:| -NanoDet-m | ShuffleNetV2 1.0x | 320*320 | 20.6 | 0.72B | 0.95M | [Download](https://drive.google.com/file/d/10h-0qLMCgYvWQvKULqbkLvmirFR-w9NN/view?usp=sharing) | -NanoDet-m-416 | ShuffleNetV2 1.0x | 416*416 | 23.5 | 1.2B | 0.95M | [Download](https://drive.google.com/file/d/1h6TBy1tx4faIBKHnYeg0QwzFF6wlFBEd/view?usp=sharing)| -NanoDet-t (***NEW***) | ShuffleNetV2 1.0x | 320*320 | 21.7 | 0.96B | 1.36M | [Download](https://drive.google.com/file/d/1O2iz-aaDiQHJNfocInpFrY8ZFMrT3M1r/view?usp=sharing) | -NanoDet-g | Custom CSP Net | 416*416 | 22.9 | 4.2B | 3.81M | [Download](https://drive.google.com/file/d/10uW7oqZKw231l_tr4C1bJWkbCXgBf7av/view?usp=sharing)| -NanoDet-EfficientLite | EfficientNet-Lite0 | 320*320 | 24.7 | 1.72B | 3.11M | [Download](https://drive.google.com/file/d/1u_t9L0jqjH858gCR-vpzWzu9FexQOSmJ/view?usp=sharing)| -NanoDet-EfficientLite | EfficientNet-Lite1 | 416*416 | 30.3 | 4.06B | 4.01M | [Download](https://drive.google.com/file/d/1y9z7BToAZOQ1pKbOjNjf79YMuFuDTvfq/view?usp=sharing) | -NanoDet-EfficientLite | EfficientNet-Lite2 | 512*512 | 32.6 | 7.12B | 4.71M | [Download](https://drive.google.com/file/d/1UMXJJxRkRzgTvN1iRKeDZqGpkLxK3X4K/view?usp=sharing) | -NanoDet-RepVGG | RepVGG-A0 | 416*416 | 27.8 | 11.3B | 6.75M | [Download](https://drive.google.com/file/d/1bsT9Ksxws2O3g_IUuUwp0QwZcJlqJw3S/view?usp=sharing) | +NanoDet-m | ShuffleNetV2 1.0x | 320*320 | 20.6 | 0.72B | 0.95M | [Download](https://drive.google.com/file/d/1ZkYucuLusJrCb_i63Lid0kYyyLvEiGN3/view?usp=sharing) | +NanoDet-m-416 | ShuffleNetV2 1.0x | 416*416 | 23.5 | 1.2B | 0.95M | [Download](https://drive.google.com/file/d/1jY-Um2VDDEhuVhluP9lE70rG83eXQYhV/view?usp=sharing)| +NanoDet-t (***NEW***) | ShuffleNetV2 1.0x | 320*320 | 21.7 | 0.96B | 1.36M | [Download](https://drive.google.com/file/d/1TqRGZeOKVCb98ehTaE0gJEuND6jxwaqN/view?usp=sharing) | +NanoDet-g | Custom CSP Net | 416*416 | 22.9 | 4.2B | 3.81M | [Download](https://drive.google.com/file/d/1f2lH7Ae1AY04g20zTZY7JS_dKKP37hvE/view?usp=sharing)| +NanoDet-EfficientLite | EfficientNet-Lite0 | 320*320 | 24.7 | 1.72B | 3.11M | [Download](https://drive.google.com/file/d/1Dj1nBFc78GHDI9Wn8b3X4MTiIV2el8qP/view?usp=sharing)| +NanoDet-EfficientLite | EfficientNet-Lite1 | 416*416 | 30.3 | 4.06B | 4.01M | [Download](https://drive.google.com/file/d/1ernkb_XhnKMPdCBBtUEdwxIIBF6UVnXq/view?usp=sharing) | +NanoDet-EfficientLite | EfficientNet-Lite2 | 512*512 | 32.6 | 7.12B | 4.71M | [Download](https://drive.google.com/file/d/11V20AxXe6bTHyw3aMkgsZVzLOB31seoc/view?usp=sharing) | +NanoDet-RepVGG | RepVGG-A0 | 416*416 | 27.8 | 11.3B | 6.75M | [Download](https://drive.google.com/file/d/1nWZZ1qXb1HuIXwPSYpEyFHHqX05GaFer/view?usp=sharing) | ****