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,

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

ResNet backbone. Args: depth (int): Depth of resnet, from {18, 34, 50, 101, 152}. stem_channels (int | None): Number of stem chan

r"""Feature Pyramid Network. This is an implementation of paper `Feature Pyramid Networks for Object Detection <https://arxiv.org/abs/1612.03

Assign a corresponding gt bbox or background to each bbox. Each proposals will be assigned with `-1`, or a semi-positive integer indicating t

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

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

BottleBlock for TridentResNet. Args: trident_dilations (tuple[int, int, int]): Dilations of different trident branch.

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

ResLayer to build ResNet style backbone. Args: block (nn.Module): block used to build ResLayer. inplanes (int): inplanes of block

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

Implementation of encoder module in `SAR. <https://arxiv.org/abs/1811.00751>`_ Args: enc_bi_rnn (bool): If True, use bidirectional R

Implements one decoder layer in DETR transformer. Args: embed_dims (int): The feature dimension. Same as `TransformerEncoderL

Implements one encoder layer in DETR transformer. Args: embed_dims (int): The feature dimension. Same as `FFN`. num_heads (int):

Node class to save decoded char indices and scores. Args: indexes (list[int]): Char indices that decoded yes. scores (list[float]

Base class for segmentation based recognizer.

Simplified version of original basic residual block. This is used in `SCNet <https://arxiv.org/abs/2012.10150>`_. - Norm layer is now optiona

Implementation of loss module for CTC-loss based text recognition. Args: flatten (bool): If True, use flattened targets, else padded targ

Base class for encode-decode recognizer.

Extract RoI features from all level feature maps levels. This is the implementation of `A novel Region of Interest Extraction Layer for Insta

HourglassNet backbone. Stacked Hourglass Networks for Human Pose Estimation. More details can be found in the `paper <https://arxiv.org/a

Parse string of one line in annotation file to dict format. Args: keys (list[str]): Keys in result dict. keys_idx (list[int]): Va

Load an image from file. Required keys are "img_prefix" and "img_info" (a dict that must contain the key "filename"). Added or updated keys a

A warpper for torch.nn.MultiheadAttention. This module implements MultiheadAttention with residual connection, and positional encoding used i

Rectification Network of RARE, namely TPS based STN in. <https://arxiv.org/pdf/1603.03915.pdf>`_. Args: num_fiducial (int): Number o

Wrap the function to be tested for torch.onnx.export tracking.

Assign a corresponding gt bbox or background to each bbox. Each proposals will be assigned with an integer indicating the ground truth index

Convert between text, index and tensor for encoder-decoder based pipeline. Args: dict_type (str): Type of dict, should be one of {'DI

Implementation of loss module for encoder-decoder based text recognition method with CrossEntropy loss. Args: ignore_index (int): Spe

Assign pixels at the center region of a bbox as positive. Each proposals will be assigned with `-1`, `0`, or a positive integer indicating th

A wrapper of concatenated dataset. Same as :obj:`torch.utils.data.dataset.ConcatDataset`, but concat the group flag for image aspect ratio.

Parse json-string of one line in annotation file to dict format. Args: keys (list[str]): Keys in both json-string and result dict.

Load annotation from annotation file, and parse instance information to dict format with parser. Args: ann_file (str): Annotation fil

Multi-Head Attention module.

Generate gt shrinked kernels for segmentation based OCR framework. Args: label_convertor (dict): Dictionary to construct label_convertor

Random sampler. Args: num (int): Number of samples pos_fraction (float): Fraction of positive samples neg_pos_up (int, op

Implement ResNet backbone for text recognition, modified from `ResNet <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: base_channels (

Implements the DETR transformer. Following the official DETR implementation, this module copy-paste from torch.nn.Transformer with modificati

Implements the decoder in DETR transformer. Args: num_layers (int): The number of `TransformerDecoderLayer`. embed_dims (int): Sa

Upsample block for DRRG and TextSnake.

Simplest RoI head, with only two fc layers for classification and regression respectively.

r"""Channel Mapper to reduce/increase channels of backbone features. This is used to reduce/increase channels of backbone features. Args:

Custom dataset for detection. The annotation format is shown as follows. The `ann` field is optional for testing. .. code-block:: none

The class for implementing DRRG and TextSnake U-Net-like FPN. DRRG: Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detectio

Feature Adaption Module. Feature Adaption Module is implemented based on DCN v1. It uses anchor shape prediction rather than feature map to

Load annotation file from hard disk to RAM. Args: ann_file (str): Annotation file path.

Computes one-to-one matching between predictions and ground truth. This class computes an assignment between the targets and the predictions

Test-time augmentation with multiple rotations in the case that img_height > img_width. An example configuration is as follows: .. code-

r"""Online Hard Example Mining Sampler described in `Training Region-based Object Detectors with Online Hard Example Mining <https://arxiv.org

Parallel Decoder module with beam-search in SAR. Args: beam_width (int): Width for beam search.

Assign a corresponding gt bbox or background to each point. Each proposals will be assigned with `0`, or a positive integer indicating the gr

Propose text components and generate local graphs for GCN to classify the k-nearest neighbors of a pivot in DRRG: Deep Relational Reasoning Graph

RegNet backbone. More details can be found in `paper <https://arxiv.org/abs/2003.13678>`_ . Args: arch (dict): The parameter of RegN

r"""ResNetV1d variant described in `Bag of Tricks <https://arxiv.org/pdf/1812.01187.pdf>`_. Compared with default ResNet(ResNetV1b), ResNetV1

Bbox sampling result. Example: >>> # xdoctest: +IGNORE_WANT >>> from mmdet.core.bbox.samplers.sampling_result import * # NOQA

Head for segmentation based text recognition. Args: in_channels (int): Number of input channels. num_classes (int): Number of out

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

Implements the encoder in DETR transformer. Args: num_layers (int): The number of `TransformerEncoderLayer`. embed_dims (int): Sa

The stem layer, stage 1 and stage 2 in Trident ResNet are identical to ResNet, while in stage 3, Trident BottleBlock is utilized to replace the

Standard anchor generator for 2D anchor-based detectors. Args: strides (list[int] | list[tuple[int, int]]): Strides of anchors

Bidirectional Corner Pooling Module (TopLeft, BottomRight, etc.) Args: in_channels (int): Input channels of module. out_channels

Convert between text, index and tensor for CTC loss-based pipeline. Args: dict_type (str): Type of dict, should be either 'DICT36' or 'DI

A wrapper of repeated dataset with repeat factor. Suitable for training on class imbalanced datasets like LVIS. Following the sampling strate

Head of CornerNet: Detecting Objects as Paired Keypoints. Code is modified from the `official github repo <https://github.com/princeton-vl/Co

Detection block in YOLO neck. Let out_channels = n, the DetectionBlock contains: Six ConvLayers, 1 Conv2D Layer and 1 YoloLayer. The firs

Graph convolutional network for clustering. This was from repo https://github.com/Zhongdao/gcn_clustering licensed under the MIT license. Arg

Hourglass Module for HourglassNet backbone. Generate module recursively and use BasicBlock as the base unit. Args: depth (int): Dept

Generate local graphs for GCN to classify the neighbors of a pivot for DRRG: Deep Relational Reasoning Graph Network for Arbitrary Shape Text

A two-feed-forward-layer module.

A wrapper of repeated dataset. The length of repeated dataset will be `times` larger than the original dataset. This is useful when the data

Res2Net backbone. Args: scales (int): Scales used in Res2Net. Default: 4 base_width (int): Basic width of each scale. Default: 26

ResNeSt backbone. Args: groups (int): Number of groups of Bottleneck. Default: 1 base_width (int): Base width of Bottleneck. Defa

ResNeXt backbone. Args: depth (int): Depth of resnet, from {18, 34, 50, 101, 152}. in_channels (int): Number of input image chann

Implementation of loss module for transformer.

ASPP (Atrous Spatial Pyramid Pooling) This is an implementation of the ASPP module used in DetectoRS (https://arxiv.org/pdf/2006.02334.pdf)

AdaptiveConv used to adapt the sampling location with the anchors. Args: in_channels (int): Number of channels in the input image

Anchor-based head (RPN, RetinaNet, SSD, etc.). Args: num_classes (int): Number of categories excluding the background categor

Build imgaug object according ImgAug argmentations.

Convert between text, index and tensor for text recognize pipeline. Args: dict_type (str): Type of dict, should be either 'DICT36' or 'DI

Custom dataset for text detection, text recognition, and their downstream tasks. 1. The text detection annotation format is as follows: