Update README.md

This commit is contained in:
JiankangDeng
2019-05-06 17:29:29 +01:00
committed by GitHub
parent 47fca7493d
commit fbb34bc352

View File

@@ -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``.