pytorch-image-comp-rnn
pytorch-image-comp-rnn copied to clipboard
Training time
I am trying to reproduce this work too. Now I am training the model. However, I find the convergence is quite slow. I trained on a TITAN X for about 9 hours, but it seems useless and the output of the network is not a picture at all. What's the training process of your model? Have you ever met this problem? And could you please tell me your email address? I want to have a discussion with you. Thanks for your help!
I don't remember how much time needed for training. It may take two or three days. You can find my email address in git log
.
Hey @1zb, any chance you can share pre-trained encoder/decoder models?