Extract c3d features, given video

vision
#1

Hi,

How to extract c3d features in Pytorch?

#2

Could you explain, what c3d features are?

#3

its a 3d convolution model for videos https://github.com/facebookarchive/C3D

#4

Would you like to extract the output activations from the 3d conv layers?
If so, you could use forward_hooks as described here

1 Like
#5

Hi Rafael： could you please give me a hand to extract c3d features, given video?

Thanks
best