About super-resolution image size and output results

tamarott / SinGAN

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

https://tamarott.github.io/SinGAN.htm

Other

3.31k stars 611 forks source link

About super-resolution image size and output results #46

Open 15732031137 opened 4 years ago

15732031137 commented 4 years ago

  First of all, congratulate your paper for getting the best ICCV 2019 paper and share your own code. I have some questions that I do n’t understand and I need to ask you. When I implement image super-resolution, execute python SR.py --input_name <LR_image_file_name>, I found The maximum size of the output image can only be 1000, but since the image I trained is 1200 or 800, the final output result is not ideal. How do I run it? wish you a happy life!

tamarott commented 4 years ago

you should change --max_size during training to be 1200 (the default is 250, which gives 1000 for x4 SR)

15732031137 commented 4 years ago

您应该在训练期间将--max_size更改为1200（默认值为250，对于x4 SR为1000）

Thank you very much for your reply and guidance!Your paper is very good, has a very high research significance, very admire you, I wish you better and better!