From 1bbedb1b7fc9f33cf4816ec13f015040a203faea Mon Sep 17 00:00:00 2001 From: "Joshua Z. Zhang" Date: Thu, 16 Mar 2017 10:30:34 -0500 Subject: [PATCH] Fix links to models --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index af624e9..0027160 100644 --- a/README.md +++ b/README.md @@ -64,7 +64,7 @@ Remember to enable CUDA if you want to be able to train, since CPU training is insanely slow. Using CUDNN is optional, it's not fully tested but should be fine. ### Try the demo -* Download the pretrained model: [`ssd_300_voc_0712.zip`](https://dl.dropboxusercontent.com/u/39265872/ssd_300_voc0712.zip), and extract to `model/` directory. (This model is converted from VGG_VOC0712_SSD_300x300_iter_60000.caffemodel provided by paper author). +* Download the pretrained model: [`ssd_300_voc_0712.zip`](https://github.com/zhreshold/mxnet-ssd/releases/download/v0.2-beta/ssd_300_voc0712.zip), and extract to `model/` directory. (This model is converted from VGG_VOC0712_SSD_300x300_iter_60000.caffemodel provided by paper author). * Run ``` # cd /path/to/mxnet-ssd @@ -78,7 +78,7 @@ python demo.py --epoch 0 --images ./data/demo/dog.jpg --thresh 0.5 This example only covers training on Pascal VOC dataset. Other datasets should be easily supported by adding subclass derived from class `Imdb` in `dataset/imdb.py`. See example of `dataset/pascal_voc.py` for details. -* Download the converted pretrained `vgg16_reduced` model [here](https://dl.dropboxusercontent.com/u/39265872/vgg16_reduced.zip), unzip `.param` and `.json` files +* Download the converted pretrained `vgg16_reduced` model [here](https://github.com/zhreshold/mxnet-ssd/releases/download/v0.2-beta/vgg16_reduced.zip), unzip `.param` and `.json` files into `model/` directory by default. * Download the PASCAL VOC dataset, skip this step if you already have one. ```