Container mainly used for lists of torch tensors. Extends lists with pytorch functionality.

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

Data loader. Combines a dataset and a sampler, and provides single- or multi-process iterators over the dataset. Note: The only differen

Class for tracker parameters.

GOT-10k dataset. Publication: GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild Lianghua Huang,

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

Wraps a network with a common backbone. Assumes the network have a 'extract_backbone_features(image)' function.

List of sequences. Supports the addition operator to concatenate sequence lists.

Class for the sequence in an evaluation.

Wraps a network to allow simple multi-GPU training.

Container mainly used for dicts of torch tensors. Extends OrderedDict with pytorch functionality.

TrackingNet dataset. Publication: TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild. Matthias Mue

LaSOT dataset. Publication: LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking Heng Fan, Liting Lin, Fan Yan

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

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

The COCO dataset. COCO is an image dataset. Thus, we treat each image as a sequence of length 1. Publication: Microsoft COCO: Common Obj

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

YoutubeVOS video object segmentation dataset. Publication: YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark Ni

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

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

Class for feature specific parameters

Multi-resolution feature extractor. args: features: List of features.

Wraps the tracker for evaluation and running purposes. args: name: Name of tracking method. parameter_name: Name of parameter file

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):

The DiMP network. args: feature_extractor: Backbone feature extractor network. Must return a dict of feature maps classifier: Ta

Scale.

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

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

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

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

AntiUAV410 dataset.

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

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.

Initializes a target model with zeros. args: filter_size: Size of the filter. feature_dim: Input feature dimentionality.

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

ResNet network module. Allows extracting specific feature blocks.

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

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 Davis VOS dataset Publication: A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation F. P

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

Pool the target region in a feature map. args: filter_size: Size of the filter. feature_stride: Input feature stride. po

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

Instance L2 normalization.

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

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

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

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

ATOM network module

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

Computes and stores the average and current value

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

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

Generate a distance map from a origin center location. args: num_bins: Number of bins in the map. bin_displacement: Displacement

r"""Experiment pipeline and evaluation toolkit for AntiUAV410 dataset. Args: root_dir (string): Root directory of AntiUAV410 dataset.