deep-high-resolution-net.pytorch icon indicating copy to clipboard operation
deep-high-resolution-net.pytorch copied to clipboard

Published 20 hours ago • verified publisher icon leoxiaobin

Double downsampling in _make_fuse_layers in pose_hrent.py only enlarges the output channel on the second downsample

Open peternaf opened this issue 5 years ago • 1 comments

for w32, it seems that the downsampling is done like this: input: 64X48 [32 channels] -> 32X24 [32 channels] -> 16X12 [128 channels] The downsample from 64X48 to 32X24 should enlarge to 64 output channels, to keep the higher resolution info saved in the inner channels, no?

peternaf avatar May 22 '20 08:05 peternaf

I have the same question. Why not 64X48 [32 channels] -> 32X24 [64 channels] -> 16X12 [128 channels]?

xuewengeophysics avatar Nov 01 '20 09:11 xuewengeophysics