search

microsoft / SGN

This is the implementation of CVPR2020 paper “Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition”.
MIT License
187 stars 56 forks source link

Great work! #3

Open desertfex opened 4 years ago

desertfex commented 4 years ago

self.spa = self.one_hot(bs, num_joint, self.seg) #(bs, 25, 20) --->[bs, 20, 25, 25] self.spa = self.spa.permute(0, 3, 2, 1).cuda() #[bs, 20, 25, 25]--->[bs, 25, 25, 20]

Can the second code be: self.spa = self.spa.permute(0, 2, 3, 1).cuda() #[bs, 20, 25, 25]--->[bs, 25, 25, 20]

The dimensions are the same. Will this make any difference? Thank you.

shuidongliu commented 4 years ago

self.spa = self.one_hot(bs, num_joint, self.seg) #(bs, 25, 20) --->[bs, 20, 25, 25] self.spa = self.spa.permute(0, 3, 2, 1).cuda() #[bs, 20, 25, 25]--->[bs, 25, 25, 20]

Can the second code be: self.spa = self.spa.permute(0, 2, 3, 1).cuda() #[bs, 20, 25, 25]--->[bs, 25, 25, 20]

The dimensions are the same. Will this make any difference? Thank you.

You can use the pretrained model to test the modified code.