search

jfzhang95 / pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
MIT License
1.2k stars 252 forks source link

size mismatch for fc8.bias: copying a param with shape torch.Size([487]) from checkpoint, the shape in current model is torch.Size([101]) #40

Open SeventhBlue opened 4 years ago

SeventhBlue commented 4 years ago

This project is very interesting, thank you bloggers for sharing. Is this model really trained on ucf101? Why is it labeled 487?

SeventhBlue commented 4 years ago

123

shanchao0906 commented 4 years ago

pretrained model应该不是用得ucf101