cszn / DnCNN

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)
https://cszn.github.io/
1.47k stars 539 forks source link

Size of input images #82

Closed Nipl0d closed 4 years ago

Nipl0d commented 4 years ago

Thank you for your code.

I have a question related to implementation of DnCNN as follows. The architecture of DnCNN has the input layer with the size of [50,50,1]. But when using the trained model for prediction, it can be applied to images of arbitrary sizes. Does we need to divide the input image into patches or replace the input layer? I didn't find this info in your paper.

Thank you in advance.