Subclass torch's LayerNorm to handle fp16.

Computes and stores the average and current value

Interpolation module.

A ResNet class that is similar to torchvision's but contains the following changes: - There are now 3 "stem" convolutions as opposed to 1, wi

conditional batchnorm

conditional batchnorm

r"""Collects the scalars broadcasted by `report()` and `report0()` and computes their long-term averages (mean and standard deviation) over us

Convenience class that behaves like a dict but allows access with the attribute syntax.

Redirect stderr to stdout, optionally print stdout to a file, and optionally force flushing on both stdout and the file.