HAT
HAT copied to clipboard
CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration
数据集
你好,请问可以提供完整数据集的下载路径 or 制作完整数据集具体方法,谢谢
how long have you spent when you train ImageNet ? and how many GPUS you used ? thank you very much !
At the beginning of the training, the PSNR is only about 10dB and it has been oscillating around 10, which does not seem to converge
运行 `python hat/test.py -opt options/test/HAT_SRx4_ImageNet-pretrain.yml` 报错如上图
I get gpu oom error when running test.py. I currently have 16G. This is not enough?
Input: ![image](https://user-images.githubusercontent.com/92149242/169640274-66a052d7-368e-499b-b2ef-232e54f6dff9.png) Output: ![image](https://user-images.githubusercontent.com/92149242/169640287-48f8fe7f-5a84-4cb4-9836-c0fbce28d2e8.png)
Rather than always going from 64 to up, can we process 640x480 images as is? I want to test how well it does without having to shrink the image to...
Hello, congratulation for getting highest score in "paperwithcode" benchmark summary. But, I curious with HAT, so I installed it. I inference an image `!python hat/test.py -opt options/test/HAT_SRx4_ImageNet-LR.yml` But, it was...