Why don't use large patch

[DEAN2012-W]

Hello,I have just read your paper,the idea of Inference of the CTformer to overcome the mosaic edge of the patch,.

I have to say it's really a good ides,but I think what about if i set the patch equal to image size((also it's resule in large Flops) alse can overcome this problem.

[wdayang]

Hi @DEAN2012-W, thanks for your interest in your work.

Yes, I agree with you large patch size can solve the mosaic edge problem. However, when the patch size is larger, there will be much greater GPU consumption since self-attention demands more GPU memory in the backpropagation. Even armed with the window attention as proposed in Swin transformer (SwinIR in deonising), a powerful GPU like 3090 can barely handle images of 512*512 with a batch size of 1.

[wdayang]

Also, smaller patch size allows larger batch size for training which indicates more diverse samples and more training stability.
So. we use smaller patch of 64*64.

[DEAN2012-W]

Thanks,your answer is really helpful for me!

[wdayang]

My pleasure！ 获取Outlook for Android<https://aka.ms/AAb9ysg>

…

________________________________ From: DEAN2012-W ***@***.***> Sent: Saturday, June 25, 2022 11:55:03 PM To: wdayang/CTformer ***@***.***> Cc: dayang_wang ***@***.***>; Comment ***@***.***> Subject: Re: [wdayang/CTformer] Why don't use large patch (Issue #7) Thanks,your answer is really helpful for me! ― Reply to this email directly, view it on GitHub<#7 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AFQCHCXYDX62R6NT5ZXVZW3VQ7IBPANCNFSM5Z3G53EQ>. You are receiving this because you commented.Message ID: ***@***.***>