Subclass torch's LayerNorm to handle fp16.

Masked Autoencoder with VisionTransformer backbone

Vision Transformer with support for global average pooling

Masked Autoencoder with VisionTransformer backbone

Masked Autoencoder with VisionTransformer backbone

Track a series of values and provide access to smoothed values over a window or the global series average.

Track a series of values and provide access to smoothed values over a window or the global series average.

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

RandomResizedCrop for matching TF/TPU implementation: no for-loop is used. This may lead to results different with torchvision's version.

LARS optimizer, no rate scaling or weight decay for parameters <= 1D.