A conv block that bundles conv/norm/activation layers. This block simplifies the usage of convolution layers, which are commonly used with a

Data structure for instance-level annotations or predictions. Subclass of :class:`BaseDataElement`. All value in `data_fields` should have th

ModuleList in openmmlab. Ensures that all modules in ``ModuleList`` have a different initialization strategy than the outer model Args:

A registry to map strings to classes or functions. Registered object could be built from registry. Meanwhile, registered functions could be c

A registry to map strings to classes or functions. Registered object could be built from registry. Meanwhile, registered functions could be c

A conv block that bundles conv/norm/activation layers. This block simplifies the usage of convolution layers, which are commonly used with a

Very simple multi-layer perceptron (also called FFN)

Data structure for pixel-level annotations or predictions. All data items in ``data_fields`` of ``PixelData`` meet the following requirements

Sequential module in openmmlab. Ensures that all modules in ``Sequential`` have a different initialization strategy than the outer model

A basic convolution block including convolution, batch norm and ReLU. Args: in_channels (int): The number of input channels. out_

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). We follow the implementation https://github.com

Implements feed-forward networks (FFNs) with identity connection. Args: embed_dims (int): The feature dimension. Same as `Mul

Compose multiple transforms sequentially. Args: transforms (Sequence[dict, callable], optional): Sequence of transform object

A general file client to access files in different backends. The client loads a file or text in a specified backend from its path and returns

A data structure interface of MMSegmentation. They are used as interfaces between different components. The attributes in ``SegDataSample`` a

Stores assignments between predicted and truth boxes. Attributes: num_gts (int): the number of truth boxes considered when computing this

A general data structure interface. It's used as the interface between different components. The following fields are convention names in MM

Compose multiple transforms sequentially. Args: transforms (list[dict | callable]): Sequence of transform object or config di

This class represents masks in the form of bitmaps. Args: masks (ndarray): ndarray of masks in shape (N, H, W), where N is th

A dictionary for config which has the same interface as python's built- in dictionary and can be used as a normal dictionary. The Config clas

This class is almost the same as official pycocotools package. It implements some snake case function aliases. So that the COCO class has the

Default constructor for optimizers. By default each parameter share the same optimizer settings, and we provide an argument ``paramwise_cfg``

This class represents masks in the form of polygons. Polygons is a list of three levels. The first level of the list corresponds to objects,

A progress bar which can print the progress. Args: task_num (int): Number of total steps. Defaults to 0. bar_width (int): Width o

Compose a data pipeline with a sequence of transforms. Args: transforms (list[dict | callable]): Either config dicts of trans

Depthwise separable convolution module. See https://arxiv.org/pdf/1704.04861.pdf for details. This module can replace a ConvModule with the

The horizontal box class used in MMDetection by default. The ``box_dim`` of ``HorizontalBoxes`` is 4, which means the length of the last dime

Image to Patch Embedding. We use a conv layer to implement PatchEmbed. Args: in_channels (int): The num of input channels. Default:

Class to visual model, log metrics (for internal use). Args: init_kwargs (dict): A dict contains the initialization keys. add_gra

A learnable scale parameter. This layer scales the input by a learnable factor. It multiplies a learnable scale parameter of shape (1,) with

Epoch-based Runner. This runner train models epoch by epoch.

Initialize module parameters with constant values. Args: val (int | float): the value to fill the weights in the module with bias

A facility for config and config files. It supports common file formats as configs: python/json/yaml. The interface is the same as a dict obj

r"""Deformable 2D convolution. Applies a deformable 2D convolution over an input signal composed of several input planes. DeformConv2d was de

Depthwise separable convolution module. See https://arxiv.org/pdf/1704.04861.pdf for details. This module can replace a ConvModule with the

Very simple multi-layer perceptron (also called FFN) with relu. Mostly used in DETR series detectors. Args: input_dim (int): Feature

The DataParallel module that supports DataContainer. MMDataParallel has two main differences with PyTorch DataParallel: - It supports a cust

ModuleList in openmmlab. Args: modules (iterable, optional): an iterable of modules to add. init_cfg (dict, optional): Initializa

A pseudo sampler that does not do sampling actually.

ResLayer to build ResNet style backbone. Args: block (nn.Module): Residual block used to build ResLayer. num_blocks (int): Number

Sequential module in openmmlab. Args: init_cfg (dict, optional): Initialization config dict.

A wrapper for ``torch.nn.MultiheadAttention``. This module implements MultiheadAttention with identity connection, and positional encoding i

ResLayer to build ResNet style backbone for RPF in detectoRS. The difference between this module and base class is that we pass ``rfp_inplane

Position encoding with sine and cosine functions. See `End-to-End Object Detection with Transformers <https://arxiv.org/pdf/2005.12872>`_ for

TensorRT engine Wrapper. Arguments: engine (tensorrt.ICudaEngine): TensorRT engine to wrap input_names (list[str]): names of each

Applies padding adaptively to the input. This module can make input get fully covered by filter you specified. It support two modes "same" an

Compose multiple transforms sequentially. Args: transforms (Sequence[dict, callable], optional): Sequence of transform object

Raise error when failed to parse pure Python style config files.

An implementation of Conv2d + BatchNorm2d with support of fusion. Modified from https://github.com/microsoft/Cream/blob/main/TinyViT/models/t

r"""Deformable 2D convolution. Applies a deformable 2D convolution over an input signal composed of several input planes. DeformConv2d was de

Convenience class that behaves like a dict but allows access with the attribute syntax.

LayerScale layer. Args: dim (int): Dimension of input features. layer_scale_init_value (float or torch.Tensor): Init value of lay

The DDP module that supports DataContainer. MMDDP has two main differences with PyTorch DDP: - It supports a custom type :class:`DataContain

Image to Patch Embedding. We use a conv layer to implement PatchEmbed. Args: in_channels (int): The num of input channels. Default:

Universal Visualizer for multiple tasks. Args: name (str): Name of the instance. Defaults to 'visualizer'. image (np.ndarray, opt

A facility for config and config files. It supports common file formats as configs: python/json/yaml. ``Config.fromfile`` can parse a diction

ContextBlock module in GCNet. See 'GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond' (https://arxiv.org/abs/1904.11492)

GeneralizedAttention module. See 'An Empirical Study of Spatial Attention Mechanisms in Deep Networks' (https://arxiv.org/abs/1711.07971) for

A residual 3D convolutional block. Args: in_channels (int): Input channels of this block. out_channels (int): Output channels of

ResLayer to build ResNet style backbone. Args: block (nn.Module): Residual block used to build ResLayer. num_blocks (int): Number

Encoder layer with window attention in Vision Transformer. Args: embed_dims (int): The feature dimension num_heads (int): Paralle

A data structure interface of MMDetection. They are used as interfaces between different components. The attributes in ``DetDataSample`` are

Wrapper class to compose multiple :class:`BaseMetric` instances. Args: metrics (dict or BaseMetric or Sequence): The config of metrics.

Standard points generator for multi-level (Mlvl) feature maps in 2D points-based detectors. Args: strides (list[int] | list[tuple[int

The base data structure of MMPose that is used as the interface between modules. The attributes of ``PoseDataSample`` includes: - ``

Worker pool that runs a function on each value that is put(). This pool is designed that if an exception is thrown in a child, the main process sh

HiViT block. Args: input_size (int): Input size. dim (int): Number of input dims. num_heads (int): Number of attention he

Cross Stage Partial Layer. Args: in_channels (int): The input channels of the CSP layer. out_channels (int): The output channels

Save checkpoints periodically. Args: interval (int): The saving period. If ``by_epoch=True``, interval indicates epochs, othe

Compose multiple transforms sequentially. Args: transforms (list[dict | callable]): Sequence of transform object or config di

Compose a data pipeline with a sequence of transforms. Args: transforms (list[dict | callable]): Either config dicts of trans

Corner Pooling. Corner Pooling is a new type of pooling layer that helps a convolutional network better localize corners of bounding boxes.

Cyclic LR Scheduler. Implement the cyclical learning rate policy (CLR) described in https://arxiv.org/pdf/1506.01186.pdf Different from

Gather-and-Expansion Layer. Args: in_channels (int): Number of input channels. out_channels (int): Number of output channels.