Nash2325138

Will using nn.AdaptiveAvgPool3d more convenient?

1

https://github.com/kenshohara/3D-ResNets-PyTorch/blob/d9847ea56b0d4bc7601a229099deb2b483539514/models/resnet.py#L139 As the title stated, is there a reason to use `nn.AvgPool3d` instead of `nn.AdaptiveAvgPool3d`? Using `nn.AdaptiveAvgPool3d` can help us get rid of calculating `last_size` and `last_duration` explicitly and passing...

https://github.com/xiadingZ/video-caption.pytorch/blob/9e4759d9a6b48a72c005bba7c3bb9c53065f1f28/models/EncoderRNN.py#L25 As the title, why do we need another linear transform layer for video features when the rnn will do it inside the cell? If it is to save the...

What are the original NSFW concepts used in the safety checker?

8

It looks like the safety checker uses some NSFW concept embeddings generated from CLIP to filter out unsafe content. I wonder if we can get the original concepts in text...