Normlize image by given mean and std.

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

A sequential module that passes timestep embeddings to the children that support it as an extra input.

Feature fusion block.

Feature fusion block.

Reduce feature maps into a single edge map

Transformer block for image-like data in temporal axis. First, reshape to b, t, d. Then apply standard transformer action. Finally, r

A downsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determini

Interpolation module.

Transformer block for image-like data in spatial axis. First, project the input (aka embedding) and reshape to b, t, d. Then apply st

An upsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determinin

Compact Dilation Convolution based Module

Compact Spatial Attention Module

Prepare sample for usage as network input.

https://github.com/evelinehong/Transformer_Relative_Position_PyTorch/blob/master/relative_position.py

Residual convolution module.

Residual convolution module.

Resize sample to given size (width, height).

Uses the CLIP transformer encoder for text (from huggingface)

Uses the OpenCLIP transformer encoder for text

Uses the T5 transformer encoder for text

Projection Model

Inception-v1 I3D architecture. The model is introduced in: Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

Pads images such that dimensions are divisible by 8

to match AttnBlock usage

Network for monocular depth estimation.

Network for monocular depth estimation.