You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
There are a couple of max_pooling2d() layers inside the attention layer sn_non_local_block_sim() which reduce the number of local features by 4 as such downsampled_num = location_num // 4. However, no downsampling step is reported in the original paper.
Also, the first two sn_conv1x1() layers, which stand for Wg and Wf in the paper, have equal sizes C/8 x C, but the third one standing for Wh has C/2 x C shape, while should be also C/8 x C. Similarly the last conv layer.
There are a couple of
max_pooling2d()
layers inside the attention layer sn_non_local_block_sim() which reduce the number of local features by 4 as such downsampled_num = location_num // 4. However, no downsampling step is reported in the original paper.Also, the first two
sn_conv1x1()
layers, which stand forWg
andWf
in the paper, have equal sizesC/8 x C
, but the third one standing forWh
hasC/2 x C
shape, while should be alsoC/8 x C
. Similarly the last conv layer.Is there a reason for such discrepancies?
Related #8
The text was updated successfully, but these errors were encountered: