practical-pytorch
practical-pytorch copied to clipboard
Correct use of "epoch" vs "iteration"
trafficstars
One epoch should be one pass over the entire dataset. In many of the tutorials, what is called an epoch is really an iteration over a single training example.
i made this and some other changes to get the generation example looking more like the char-rnn architecture https://gist.github.com/kylemcdonald/2d06dc736789f0b329e11d504e8dee9f
some of this is specific to the direction i'm going, but other parts might be useful for what you're doing?
thanks for the tutorials!