deepak112/Keras-SRGAN

Colour of output image is off

rcbrigg opened this issue · 2 comments

I am finding that image generated often appears to be under-saturated. I might be able to remap the output image to match the mean and variance of the input image, but I don't see understand why the network won't be doing this itself. Is this normal or am I missing something?

gan_generated_image_epoch_627

Dear Sir,
Brilliant work , thank you for sharing your code..
Please, according to your GPU version what the time did you take to finish training your network ??
I'm waiting for your fast reply..

Please all,
I need the code of implementation this part
the part is

{The SRResNet networks
were trained with a learning rate of 10−4 and 106 update
iterations. We employed the trained MSE-based SRResNet
network as initialization for the generator when training
the actual GAN to avoid undesired local optima.{