Wuyanger
Wuyanger
I found almost each SRGAN doesn't well in jpg's img.I want to know what's the problem? Is it because the SRGAN's structure,or the dataset? If I convert the DIV2K‘s form...
Hi,thank you for sharing this project! I'm excited and I wanna train it at once.When I reading the imgs,most of the imgs readed normally,but some imgs have problem like this:...
First of all,thanks for your model! And there is a question:when I use my own png image,I found it didn't work as well as the default image,I thought maybe it...
I have downloaded the ImageNet folder,and these images are of different sizes,should I crop them first and then put them into data/train?