Very simple multi-layer perceptron (also called FFN)

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

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

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

Computes and stores the average and current value

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.

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

r""" ConvNeXt A PyTorch impl of : `A ConvNet for the 2020s` - https://arxiv.org/pdf/2201.03545.pdf Args: in_chans (int

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

This class computes an assignment between the targets and the predictions of the network For efficiency reasons, the targets don't include the no_

This is a 2D attention module, which only returns the attention softmax (no multiplication by value)

Simple convolutional head, using group norm. Upsampling is done using a FPN approach

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

This module converts the model's output into the format expected by the coco api

This class converts the output of the model to the final panoptic result, in the format expected by the coco panoptic API

This class computes the loss for Conditional DETR. The process happens in two steps: 1) we compute hungarian assignment between ground tr

This class computes an assignment between the targets and the predictions of the network For efficiency reasons, the targets don't include the no_

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

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

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

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

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

Inherit from this class and define ``__nice__`` to "nicely" print your objects. Defines ``__str__`` and ``__repr__`` in terms of ``__nice__``

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

Randomly selects between transforms1 and transforms2, with probability p for transforms1 and (1 - p) for transforms2

Randomly selects between transforms1 and transforms2,