Very simple multi-layer perceptron (also called FFN)

A simple timer.

config files. only support .py file as config now. ref: mmcv.utils.config Example: >>> cfg = Config(dict(a=1, b=dict(b1=[0,

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

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

Simple block, preserve spatial resolution.

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

ResNet backbone with frozen BatchNorm.

A basic Swin Transformer layer for one stage. Args: dim (int): Number of feature channels depth (int): Depths of this stage.

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

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

Hourglass Decoder

Downsampling block for use in encoder.

Downsampling block for use in encoder.

Hourglass Encoder

GRN (Global Response Normalization) layer

gradio for human

gradio for animal

Hourglass architecture.

Wrapper for Human

Wrapper for Animal

Multilayer perceptron.

Image to Patch Embedding Args: patch_size (int): Patch token size. Default: 4. in_chans (int): Number of input image channels. De

Absolute pos embedding, learned.

This is a more standard version of the position embedding, very similar to the one used by the Attention is all you need paper, generalized t

Res block, preserve spatial resolution.

Swin Transformer backbone. A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows` - https:/

Swin Transformer Block. Args: dim (int): Number of input channels. num_heads (int): Number of attention heads. window_siz

This is the Cross-Attention Detector module that performs object detection

Upsampling block for use in decoder.

Window based multi-head self attention (W-MSA) module with relative position bias. It supports both of shifted and non-shifted window. Args:

Upsampling block for use in decoder.

argparse action to split an argument into KEY=VALUE form on the first = and append to a dictionary. List options should be passed as comm

This class takes as input a set of embeddings of dimension C1 and outputs a set of embedding of dimension C2, after a linear transformation,

BatchNorm2d where the batch statistics and the affine parameters are fixed. Copy-paste from torchvision.misc.ops with added eps before rqsrt

landmark runner

r"""Allows the model to jointly attend to information from different representation subspaces. See reference: Attention Is All You Need ..

IoULoss. Computing the oks loss between a set of predicted poses and target poses. Args: linear (bool): If True, use linear scale of l

Patch Merging Layer Args: dim (int): Number of input channels. norm_layer (nn.Module, optional): Normalization layer. Default: n

This is a more standard version of the position embedding, very similar to the one used by the Attention is all you need paper, generalized t

Printable Config defining str function