Masked Autoencoder with VisionTransformer backbone

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

Diffusion Loss

The final layer adopted from DiT.

Utilities for training and sampling diffusion models. Original ported from this codebase: https://github.com/hojonathanho/diffusion/blob/

A residual block that can optionally change the number of channels. :param channels: the number of input channels.

The MLP for Diffusion Loss. :param in_channels: channels in the input Tensor. :param model_channels: base channel count for the model.

A diffusion process which can skip steps in a base diffusion process. :param use_timesteps: a collection (sequence or set) of timesteps from

Embeds scalar timesteps into vector representations.

Which type of output the model predicts.

What is used as the model's output variance. The LEARNED_RANGE option has been added to allow the model to predict values between FIXED_S