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

ConvNeXt V2 Args: in_chans (int): Number of input image channels. Default: 3 num_classes (int): Number of classes for classificat

Corss attention conditioning An attention block that allows spatial positions to attend to each other. Originally ported from here, but a

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

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

LayerNorm that supports two data formats: channels_last (default) or channels_first. The ordering of the dimensions in the inputs. channels_last c

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

The full UNet model with attention and timestep embedding. :param in_channels: channels in the input Tensor. :param model_channels: base

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

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

MLP as used in Vision Transformer, MLP-Mixer and related networks

A module which performs QKV attention and splits in a different order.

SuperPoint Convolutional Detector and Descriptor SuperPoint: Self-Supervised Interest Point Detection and Description. Daniel DeTone, Tomasz

ConvNeXtV2 Block. Args: dim (int): Number of input channels. drop_path (float): Stochastic depth rate. Default: 0.0

ConvNeXt Block There are two equivalent implementations: (1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N

IMPORTANT: this model is in (v b), NOT (b v), due to some historical issues. keep this in mind when performing any operation related to the view d

GRN (Global Response Normalization) layer

Pads images such that dimensions are divisible by 8

A Local Feature Transformer (LoFTR) module.

A module which performs QKV attention. Matches legacy QKVAttention + input/ouput heads shaping

self attention + cross attention + FFN

Wraps a dataset so that PyTorch Lightning's validation step can be turned into a visualization step.

Adapted from CLIP: https://github.com/openai/CLIP/blob/main/clip/model.py