Training image patches
Shakarim94 opened this issue · 2 comments
Shakarim94 commented
In the paper you use various datasets (BSD500, Waterloo etc.) that have various sized images. For training 128x128 sized patches are used. Could you give information about the number of patches extracted (Like in DnCNN paper)? So basically I want to know the dimensions of the training dataset ?x128x128x3. Also did you use any data augmentation methods?
GuoShi28 commented
I did not use any data augmentation methods. I just count the training data. The number of training data if about 10260 Batches. In our experiments, I set the batch size equal to 36, which means the total training data is 10260361281283
Shakarim94 commented
Understood. Thank you very much