RLFN issues

New Super-Resolution Benchmarks

Hello, [MSU Graphics & Media Lab Video Group](https://videoprocessing.ai/) has recently launched two new Super-Resolution Benchmarks. * [Video Upscalers Benchmark: Quality Enhancement](https://videoprocessing.ai/benchmarks/video-upscalers.html) determines the best upscaling methods for increasing video resolution...

EvgeneyBogatyrev

about Contrastive Loss

1

Hi, thanks for your great work! I have a question about contrastive loss. What does (Ypos, Yneg, Yanchor) stand for?

jhl13

conv_f 在ESA strcture中的作用

1

Hi: 请问下model/rlfn_ntire.py中class ESA中的self.conv_f的作用是什么，在论文中Figure 3的ESA的结构中没有这个卷积层？

Jillian2017

训练模型

1

请问可不可以提供一下×2 的训练模型呀，非常感谢然后论文里面一些其他的方法的预训练模型方便分享吗

zhangzheng2242

About feature extractor

How is the structure of a feature extractor ？ Is there just one Conv k3s1-Tanh-Conv k3s1 ?

Legenhoor

Can you provide the code about contrastive loss?

Thanks for sharing your code. I want to reproduce your work, but I can't find code about contrastive loss and contrastive module. Can you provide it?

wangqiim

Question

2

How to visualize the extracted features?

wwang0107

How many iterations of the model can you get the best performance in the benchmark？

1

Benchmark like Set5, Set14 and so on. According to the paper, the initial learning rate is 5e-4, and is halved every 2e5 iterations, but the total number of iterations is...

DyCheer