Closed zhaozhengChen closed 4 years ago
In the paper, steps are the number of batches. In the code, the step variable contains the number of images seen so far: https://github.com/google-research/mixmatch/blob/master/libml/train.py#L49
So paper steps = code steps / batch. 1024*1024 / 64 = 16384
Sorry to comment on a closed issue but I feel it's related. The batch is 64 for the labeled samples, but also 64 for the unlabeled samples, that gives a total batch size of 128. I believe you just count labeled samples for the purpose of defining steps and keeping track of the training length, is that correct? Thanks in advance
Hi,
In section 3.5 of your paper:
But the implementation of lambda seems to ramp up lambda_u in 1024 epochs(1024*1024 steps).