Tensorflow training becomes slower and slower when iteration is more than 10,000. Why?
|Added at||2016-12-28 02:12|
I feed the data to the graph with input pipeline methods, and tf.train.shuffle_batch is implemented to generate batch data. However, with the training going, tensorflow becomes slower and slower for later iterations. I am confused about what's the essential reason leading to it? Thanks very much! My code snippet is: