Keras-SRGAN
Keras-SRGAN copied to clipboard
FailedPreconditionError: Error while reading resource variable _AnonymousVar411 from Container: localhost. This could mean that the variable was uninitialized. Not found: Resource localhost/_AnonymousVar411/class tensorflow::Var does not exist. [[node mul_168/ReadVariableOp (defined at C:\Users\ASUS\AppData\Local\conda\conda\envs\tensor flow\lib\site-packages\keras\backend\tensorflow_backend.py:3009) ]] [Op:__inference_keras_scratch_graph_18040] Function call stack: keras_scratch_graph
Hi Deepak, this is the error i get after starting the training, somehow it seems that some variables are not initialized.
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.{
I also have this problem. Have you solved it?