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

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

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.

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

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

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. https

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. https

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. https

Defines a PatchGAN discriminator as in Pix2Pix --> see https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/models/networks.py

A single linear layer which does a 1x1 conv

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

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

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

output 3 levels of features using a FPN structure

output 3 levels of features using a FPN structure

This model is not sensitive to finetuning

This model is not sensitive to finetuning

Coarse-to-fine sparse cost regularization network return sparse volume feature for extracting sdf

Coarse-to-fine sparse cost regularization network return sparse volume feature for extracting sdf

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

Uses the CLIP transformer encoder for text (from huggingface)

Uses the CLIP transformer encoder for text (from huggingface)

Pre-trained network with all channels equally weighted by default

Pre-trained network with all channels equally weighted by default

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

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

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

3D self-attention

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

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

A named tuple describing a ResNet block.

A named tuple describing a ResNet block.