search

vt-vl-lab / 3d-photo-inpainting

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
https://shihmengli.github.io/3D-Photo-Inpainting/
Other
6.91k stars 1.11k forks source link

Video fails to generate, fails on line 95 torch.load #113

Open rafaelola opened 3 years ago

rafaelola commented 3 years ago

My machine is ubuntu 20.04, I have nvcc version 10.0 python v 3.7, when I run the command, I get this error:

Traceback (most recent call last): File "main.py", line 95, in rgb_feat_weight = torch.load(config['rgb_feat_model_ckpt'], File "/home/develo-1/anaconda3/envs/3DP/lib/python3.8/site-packages/torch/serialization.py", line 595, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "/home/develo-1/anaconda3/envs/3DP/lib/python3.8/site-packages/torch/serialization.py", line 781, in _legacy_load deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly) RuntimeError: unexpected EOF, expected 1630865 more bytes. The file might be corrupted.

any tips would be welcome please.

dkostenko commented 3 years ago

Try to download models again - it helped me