Training transition model is too resource intensive, uses too much memory. Possible bug about research

[EderSantana]

it is super resource intensive yes. I saw elsewhere that Keras does a lot of memory leaks. I used to have a tensorflow only implementation that seemed lighter. But it was less convenient, that was why I opted for Keras in the release.

[sunny1986]

@kamal94 : Were you able to resolve that issue? I am having the same problem and my train fails sometimes on epoch 1/200 or 2/200 and never goes beyond that. Any suggestions??

[zhaohuaqing1993]

how do you train the train_generative_model.py autoencoder successfully ,i meet some difficuty , have to doing somehting in code?

[pandamax]

Have you solved this issue? I am having the same problem and my train fails sometimes on epoch 10/200 or 40/200 and never goes beyond that. Any suggestions?
Traceback (most recent call last):
File "./train_generative_model.py", line 168, in
nb_epoch=args.epoch, verbose=1, saver=saver
File "./train_generative_model.py", line 84, in train_model
z, x = next(generator)
File "./train_generative_model.py", line 31, in gen
X = cleanup(tup)
File "/home/deep-learning/research-master/models/transition.py", line 34, in cleanup
X = X/127.5 - 1.
MemoryError