From 83fc4684d8e72861ea5778c776e147d06ad15cab Mon Sep 17 00:00:00 2001 From: nagadomi Date: Sat, 8 Oct 2016 19:54:02 +0900 Subject: [PATCH] update Benchmark.md --- appendix/benchmark.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/appendix/benchmark.md b/appendix/benchmark.md index de52143..fbea981 100644 --- a/appendix/benchmark.md +++ b/appendix/benchmark.md @@ -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 -model1_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 | |---------------|---------------|---------------|------------------|------------------|