CodeMirror/waifu2x
1
0
Fork 0
mirror of synced 2024-05-16 19:02:21 +12:00
Code Issues Releases Wiki Activity

update Benchmark.md

Browse source
This commit is contained in:
nagadomi 2016-10-08 19:54:02 +09:00
parent 6f437e4014
commit 83fc4684d8
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
appendix/benchmark.md
View file

@ -3,7 +3,7 @@
## Photo
Note: waifu2x's photo models was trained on [kou's photo collection](http://photosku.com/photo/category/%E6%92%AE%E5%BD%B1%E8%80%85/kou/).
Note: PSNR in this benchmark uses a MATLAB's rgb2ycbcr compatible function(dynamic range [16 235], not [0, 255]) for converting grayscale image. I think it's not correct PSNR. But many paper used this metric.
Note: PSNR in this benchmark uses a [MATLAB's rgb2ycbcr](https://jp.mathworks.com/help/images/ref/rgb2ycbcr.html?lang=en) compatible function (dynamic range [16 235], not [0 255]) for converting grayscale image. I think it's not correct PSNR. But many paper used this metric.
command:
`th tools/benchmark.lua -dir <dataset_dir> -model1_dir <model_dir> -method scale -filter Catrom -color y -range_bug 1 -tta <0|1> -force_cudnn 1`
@ -22,7 +22,7 @@ Urban100: https://github.com/jbhuang0604/SelfExSR
### 2x with TTA - PSNR
Note: TTA is an ensemble technique that is supported by waifu2x. This method is 8x slower than non TTA method but it improves PSNR (~+0.1 on photo, ~+0.4 on art).
Note: TTA is an ensemble technique that is supported by waifu2x. TTA method is 8x slower than non TTA method but it improves PSNR (~+0.1 on photo, ~+0.4 on art).
| Dataset/Model | Bicubic | vgg\_7/photo | upconv\_7/photo | upconv\_7l/photo |
|---------------|---------------|---------------|------------------|------------------|