Jiu XU

This is the reason of python's version, please check https://github.com/twtygqyy/pytorch-vdsr/issues/21

Hi @DanChen001 , for training with multiple h5 files, I think you need to modify the data generator. You can allocate memory to a certain number of patches in the...

Hi @YNX940214 The size you mentioned about the augmented data is correct, and it does take longer than 4 hours to train in this implementation. The reason is mainly about...

@CHELSEA234 Thanks for your interests. Could you please check if the bicubic performance is close to the result on the paper? Also please save the bicubiced images in mat format...

@CHELSEA234 For the data augmentation, following the paper, I used flipping, rotation (90 180 270 degree) and downsizing (scaling factor from 1 to 0.5). For the matlab.engine, I did that...

@CHELSEA234 All hyperparameters I used for training are provided in this repository with default settings. I guess the only reason leads to the difference is because the way of calculating...

Hi @CHUANGQIJI "We provide a simple hdf5 format training sample in data folder with 'data' and 'label' keys, the training data is generated with Matlab Bicubic Interpolation, please refer Code...

@CHUANGQIJI 需要在训练的时候加上 --cuda 不然就是用cpu训练了

@chenwang0205 请确认是否依照Code for Data Generation生成自己的训练数据

@flystarhe Please set threads=1