leaderj1001 / Stand-Alone-Self-Attention

Implementing Stand-Alone Self-Attention in Vision Models using Pytorch
MIT License
456 stars 83 forks source link

How can you v_out_h + self.rel_h #4

Open yt605155624 opened 5 years ago

yt605155624 commented 5 years ago

Hello ,the v_out_h 's shape is [n,c//2,kernel_sizeh,kernel_sizew] ,but the self.rel_h 's shape is [out_channels // 2, 1, 1, kernel_size, 1 ] ,how can you add these two different shape ? hope your early reply!

leaderj1001 commented 5 years ago

Thank you for your comments. I just using element-wise sum.

Thank you !