In WDSR-B, why not do the 3x3 Conv without the second 1x1 Conv?

JiahuiYu / wdsr_ntire2018

Code of our winning entry to NTIRE super-resolution challenge, CVPR 2018

http://www.vision.ee.ethz.ch/ntire18/

598 stars 123 forks source link

In WDSR-B, why not do the 3x3 Conv without the second 1x1 Conv? #43

Closed splinter21 closed 4 years ago

splinter21 commented 4 years ago

WDSR-A x/2->2x->x/2 computation: 3x3x2/2+3x3x2/2=18 act: 2 3x3Conv: 100%

WDSR-B: x->6x->0.8x->x computation: 6+6x0.8+3x3x0.8=18 act: 6 3x3Conv: 40% (I think you use the second 1x1 Conv just to align the computation with one EDSR block and WDSR-A block)

WDSR-B-modified: x/2->3x->x/2 computation: 3/2+3/2x3x3=15 act: 3 3x3Conv: 90% So you can compare the performance: WDSR-A-B5 vs. WDSR-B-modified-B6.

JiahuiYu commented 4 years ago

@splinter21 Why not have a try? Do you have any performance evaluation?