how to recover performance when doing evaluation about mixmatch HOT 4 CLOSED

When we save a checkpoint, we save the EMA model weights. Then when you restore you get the restored EMA weights and can use those directly.

from mixmatch.

Thanks for your response. Just to confirm what you mean, so you are saying the EMA model weights are already saved in the code, and when we use saver.restore(sess, save_path) we already get the EMA weights? Or are you saying people who uses the code should do it themselves?

from mixmatch.

Both are saved if I remember correctly. If you run

then you should be able to see both the raw (no EMA) and EMA model predictions.

from mixmatch.

In the code snippet what is the self.tune(16384) doing? why 16384?

Thanks again, I'm really interested in your work!

from mixmatch.