Unable to untar the pre-trained VCN model weights

gengshan-y / VCN

Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019.

https://gengshan-y.github.io/VCN/

MIT License

154 stars 25 forks source link

Closed pichuang1984 closed 4 years ago

pichuang1984 commented 4 years ago

Hi,

Thanks so much for open-sourcing your work!

I am trying to load your pre-trained model weights from (https://drive.google.com/drive/folders/1mgadg50ti1QdwfAf6aR2v1pCx-ITsYfE?usp=sharing) but I am not able to untar the finetune_149999.tar from neither "chairs" or "kitti-ft-trainval". Below is the error message:

tar -xvf finetune_149999.tar
tar: Error opening archive: Unrecognized archive format

gengshan-y commented 4 years ago

Hi, don't need to untar it. You can just use the original .tar file. This confusing suffix is a pytorch convention.

pichuang1984 commented 4 years ago

Ah thanks! I was under the impression that pytorch checkpoint often ends with *.pth.tar. Will close the issue.