search

hche11 / VGGSound

VGGSound: A Large-scale Audio-Visual Dataset
http://www.robots.ox.ac.uk/~vgg/data/vggsound/
Other
285 stars 31 forks source link

Pretrained file is damaged #10

Closed AyaneAI closed 3 years ago

AyaneAI commented 3 years ago

Thanks for your great contribution. I try to download "vggsound_avgpool" of model H, but the file is damaged. It is appreciated it if you can upload the file again!

hohsiangwu commented 3 years ago

Actually, I found that you can just load the .tar model file directly with torch.load and it works.

checkpoint = torch.load('vggsound_avgpool.pth.tar')