Open DonaldTsang opened 5 years ago
@nagadomi so Resnet > Upconv > VGG for all types... I would like to request a few things:
If you want it, do it yourself. The above benchmark describes the results of BSD100 and Urban100, and the results are also described in other papers. Note that waifu2x is not overfitting to fixed bicubic downsampling.
Here are benchmarks done by somebody else:
Here are collections/toolkit collections:
And here is a list of models:
Requesting accuracy, training speed and processing speed (in both seconds and Add-Mult/FLOPS ) benchmarks of different models for Waifu2x e.g. VGG vs ResNet vs Inception (of different sizes)
If you can go the extra mile, compare algorithms with: