Closed calmarazAM closed 4 years ago
A lot of code is shared but there are some differences that could be significant:
Note that MixMatch is also present in the FixMatch code base, so maybe working off the FixMatch code base would be a better alternative.
Hi, I also noticed that you changed the way of weight decay from post_ops.extend([tf.assign(v, v * (1 - wd)) for v in utils.model_vars('classify') if 'kernel' in v.name])
(in MixMatch) to loss_wd = sum(tf.nn.l2_loss(v) for v in utils.model_vars('classify') if 'kernel' in v.name)
(in FixMatch). Do you have any reasons for this change?
Thanks!
Because we changed the optimizer from Adam to momentum. L2 penalty doesn't play well with Adam in particular from what I understand and that's why we used weight decay back in MixMatch.
Thanks. I didn't read that part in the paper. It's very helpful information.
Hi!
Congrats on the paper, I'm excited to try FixMatch on my own dataset. I actually have previously used your code for MixMatch and I was wondering if this new repo is fully compatible with it, i.e., have there been any changes in the implementation of the common files between the two repos?
Thanks! :)