kami93 / predrnn Goto Github PK

i use tf2.0 met some problem. can u share which version of tensorflow do you use? Thanks!

when I even set batch_size = 1 (Moving MNIST) on my single GPU(1080Ti 11G) , the program run at predRNN.fit() function, and crash suddenly. Is it because shortage of GPU memory about PredRNN net with STLSTM?

After successfully trained model with STLSTM layer, when I tried to save the model in keras, got the following error:

Error in py_call_impl(callable, dots$args, dots$keywords) :
ValueError: tf.function-decorated function tried to create variables on non-first call.

I had to disable eager execution in my code for compatibility reasons, which could be causing the problem:
tf.compat.v1.disable_eager_execution()
tf.compat.v1.disable_control_flow_v2()

How can we fix it? Thanks