kidwhh

My image has been cut to a resolution of 224*224. Can I use this model to detect feature points

问一下大家目前尝试的最好的结果是什么了

2

我看实现的最好的结果PSNR在22-23之间，有没有更好一些的了，或者实现出原论文的效果的了？

about Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]

1

I saw that Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5] was used for the input data when the train was made.Face_verify.py is also used, why is Normalize not used when evaluating...

i can not down all file ，miss some file ，i do not know the reason

关于FAN的输入问题

1

FAN网络的输入图像好像必须分辨率是2的k次方这种，有什么方法能解决这个问题吗，使非2^k的图像也能输入？

关于预训练模型

8

Can you tell me how epochs/fan_psnr_x4.pth and fan_gan_x4.pth are used respectively? I didn't find a place in the code to load the two pre-training models.Thank you very much