Alex Nguyen

Numpy-like interaction with tensors

6

As our random variables are now tensors, manipulations that users of pymc3 are familiar with might no longer be valid, requiring them to use tensorflow's particular syntax for manipulating tensors....

Hello there, thank you for the very intriguing paper ! I was interested in studying your results, and I find it hard to find the parameters that you used for...

Understanding EMA loss implementation

1

Hi, I'm curious about your implementation of the EMA loss ``` def ema_loss(x, running_mean, alpha): t_exp = torch.exp(torch.logsumexp(x, 0) - math.log(x.shape[0])).detach() if running_mean == 0: running_mean = t_exp else: running_mean...