Training dataset structure about srgan-pytorch

[Lornatang]

Reference from origin paper Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial
Network

# 3.2
3.2. Training details and parameters
We trained all networks on a NVIDIA Tesla M40 GPU using a random sample of 
350 thousand images from the ImageNet database [44]. These images are distinct
 from the testing images. We obtained the LR images by downsampling the HR 
images (BGR, C = 3) using bicubic kernel with downsampling factor r = 4. For 
each mini-batch we crop 16 random 96 × 96 HR sub images of distinct training 
images. Note that we can apply the generator model to images of arbitrary size 
as it is fully convolutional. For optimization we use Adam [35] with β1 = 0.9. 

[dokluch]

Reference from origin paper Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

# 3.2
3.2. Training details and parameters
We trained all networks on a NVIDIA Tesla M40 GPU using a random sample of 
350 thousand images from the ImageNet database [44]. These images are distinct
 from the testing images. We obtained the LR images by downsampling the HR 
images (BGR, C = 3) using bicubic kernel with downsampling factor r = 4. For 
each mini-batch we crop 16 random 96 × 96 HR sub images of distinct training 
images. Note that we can apply the generator model to images of arbitrary size 
as it is fully convolutional. For optimization we use Adam [35] with β1 = 0.9. 

Thank you. As for the structure, I've also figured out I have to name the folders train and test, not train and valid (for DIV2k)