提交 f976dcc1 编写于 作者: N Nathan Ng

Updated links

上级 cf94b42e
......@@ -52,8 +52,8 @@ You can download these from AWS. You just have to put `data_2d_h36m_cpn_ft_h36m_
```sh
cd data
wget https://s3.amazonaws.com/video-pose-3d/data_2d_h36m_cpn_ft_h36m_dbb.npz
wget https://s3.amazonaws.com/video-pose-3d/data_2d_h36m_detectron_ft_h36m.npz
wget https://dl.fbaipublicfiles.com/video-pose-3d/data_2d_h36m_cpn_ft_h36m_dbb.npz
wget https://dl.fbaipublicfiles.com/video-pose-3d/data_2d_h36m_detectron_ft_h36m.npz
cd ..
```
......@@ -97,6 +97,6 @@ We provide support for the following 2D detections:
Since HumanEva is very small, we do not fine-tune the pretrained models. As before, you can download Mask R-CNN detections from AWS (`data_2d_humaneva15_detectron_pt_coco.npz`, which must be copied to `data/`). As before, we have included detections for unlabeled subjects/actions. These begin with the prefix `Unlabeled/`. Chunks that correspond to corrupted motion capture streams are also marked as unlabeled.
```sh
cd data
wget https://s3.amazonaws.com/video-pose-3d/data_2d_humaneva15_detectron_pt_coco.npz
wget https://dl.fbaipublicfiles.com/video-pose-3d/data_2d_humaneva15_detectron_pt_coco.npz
cd ..
```
\ No newline at end of file
```
......@@ -44,8 +44,8 @@ The pretrained models can be downloaded from AWS. Put `pretrained_h36m_cpn.bin`
```sh
mkdir checkpoint
cd checkpoint
wget https://s3.amazonaws.com/video-pose-3d/pretrained_h36m_cpn.bin
wget https://s3.amazonaws.com/video-pose-3d/pretrained_humaneva15_detectron.bin
wget https://dl.fbaipublicfiles.com/video-pose-3d/pretrained_h36m_cpn.bin
wget https://dl.fbaipublicfiles.com/video-pose-3d/pretrained_humaneva15_detectron.bin
cd ..
```
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册