The program got stuck, when I expand datasets to distributed_tf_sample.py about misc HOT 2 CLOSED

Thanks for your advices, I have fixed the program.

from misc.

I think this happens because the data is big when you run validation (or test):

acc = sess.run(m.accuracy, feed_dict={m.inp: mnist.validation.images,
                                                      m.labels: mnist.validation.labels})

.....

acc = sess.run(m.accuracy, feed_dict={m.inp: mnist.test.images, m.labels: mnist.test.labels})

This is the whole validation/test set. In my example code, the validation/test set only has 10000 samples, but it might be a lot bigger in your dataset (?)

The way to fix this is to iterate over the validation/test set, and only compute for each batch sequentially, then you average the results.

from misc.