From fbb34bc352f70edd4e12dfe3e7b91b9551f7f770 Mon Sep 17 00:00:00 2001 From: JiankangDeng Date: Mon, 6 May 2019 17:29:29 +0100 Subject: [PATCH] Update README.md --- RetinaFace/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/RetinaFace/README.md b/RetinaFace/README.md index 670f6e4..7fa39e9 100644 --- a/RetinaFace/README.md +++ b/RetinaFace/README.md @@ -42,9 +42,9 @@ Please check ``train.py`` for training. 1. Copy ``rcnn/sample_config.py`` to ``rcnn/config.py`` 2. Download pretrained models and put them into ``model/``. -&ensp ImageNet ResNet50 ([baidu cloud](https://pan.baidu.com/s/1WAkU9ZA_j-OmzO-sdk9whA) and [dropbox](https://www.dropbox.com/s/48b850vmnaaasfl/imagenet-resnet-50.zip?dl=0)). + ImageNet ResNet50 ([baidu cloud](https://pan.baidu.com/s/1WAkU9ZA_j-OmzO-sdk9whA) and [dropbox](https://www.dropbox.com/s/48b850vmnaaasfl/imagenet-resnet-50.zip?dl=0)). -&ensp ImageNet ResNet152 ([baidu cloud](https://pan.baidu.com/s/1nzQ6CzmdKFzg8bM8ChZFQg) and [dropbox](https://www.dropbox.com/s/8ypcra4nqvm32v6/imagenet-resnet-152.zip?dl=0)). + ImageNet ResNet152 ([baidu cloud](https://pan.baidu.com/s/1nzQ6CzmdKFzg8bM8ChZFQg) and [dropbox](https://www.dropbox.com/s/8ypcra4nqvm32v6/imagenet-resnet-152.zip?dl=0)). 3. Start training with ``CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --prefix ./model/retina --network resnet``. Before training, you can check the ``resnet`` network configuration (e.g. pretrained model path, anchor setting and learning rate policy etc..) in ``rcnn/config.py``.