Tensorflow memory leak in every iteration

Question

I\'m trying to find out why the code below occurs a huge memory leak during iteration by iteration. Here\'s the whole code.

def train_network(file_folder, fi         


        

Answer 1

The reason is you create new tensorflow operations on every session call.

Move these two out of for loop tf.gather(class_logit, 0), tf.gather(highlight_logit, 0), and problem should gone.