A conv block that contains conv/norm/activation layers. Args: in_channels (int): Same as nn.Conv2d. out_channels (int): Same as n

Assign a corresponding gt bbox or background to each bbox. Each proposals will be assigned with `-1`, `0`, or a positive integer indicating t

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

Examples: >>> from mmdet.core import AnchorGenerator >>> self = AnchorGenerator(9, [1.], [1.]) >>> all_anchors = self.gri

Assign a corresponding gt bbox or background to each bbox. Each proposals will be assigned with `-1`, `0`, or a positive integer indicating t

A MaskedConv2d which inherits the official Conv2d. The masked forward doesn't implement the backward function and only supports the stride pa

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

Online Hard Example Mining Sampler described in [1]_. References: .. [1] https://arxiv.org/pdf/1604.03540.pdf

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

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

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

FP16 optimizer hook. The steps of fp16 optimizer is as follows. 1. Scale the loss value. 2. BP in the fp16 model. 2. Copy gradients f

Example: >>> # xdoctest: +IGNORE_WANT >>> from mmdet.core.bbox.samplers.sampling_result import * # NOQA >>> self = Sampl

A learnable scale parameter

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

Basic residual block. This block is a little different from the block in the ResNet backbone. The kernel size of conv1 is 1 in this block whi

Sampler that restricts data loading to a subset of the dataset. It is especially useful in conjunction with :class:`torch.nn.parallel.Distribu

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

High-Resolution Module for HRNet. In this module, every branch has 4 BasicBlocks/Bottlenecks. Fusion/Exchange is in this module.

Non-local module. See https://arxiv.org/abs/1711.07971 for details. Args: in_channels (int): Channels of the input feature map.

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

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

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection ATSS head structure is similar wi

BFP (Balanced Feature Pyrmamids) BFP takes multi-level features as inputs and gather them into a single one, then refine the gathered feature

Balanced L1 Loss arXiv: https://arxiv.org/pdf/1904.02701.pdf (CVPR 2019)

Base class for detectors

Collect data from the loader relevant to the specific task. This is usually the last stage of the data loader pipeline. Typically keys i

r"""More general bbox head, with shared conv and fc layers and two optional separated branches. /-> cls convs ->

Custom dataset for detection. Annotation format: [ { 'filename': 'a.jpg', 'width': 1280, 'height'

Default formatting bundle. It simplifies the pipeline of formatting common fields, including "img", "proposals", "gt_bboxes", "gt_labels", "g

A Deformable Conv Encapsulation that acts as normal Conv layers. Args: in_channels (int): Same as nn.Conv2d. out_channels (int):

r"""Bbox head used in Double-Head R-CNN /-> cls /-> shared convs ->

Random expand the image & bboxes. Randomly place the original image on a canvas of 'ratio' x original image size filled with mean values. The

Fully Convolutional One-Stage Object Detection head from [1]_. The FCOS head does not use anchor boxes. Instead bounding boxes are predi

FoveaBox: Beyond Anchor-based Object Detector https://arxiv.org/abs/1904.03797

r"""Multi-level fused semantic segmentation head. in_1 -> 1x1 conv --- | in_2 -> 1x1 conv -- |

Guided-Anchor-based RPN head.

Guided-Anchor-based RetinaNet head.

GHM Classification Loss. Details of the theorem can be viewed in the paper "Gradient Harmonized Single-stage Detector". https://arxiv.org

GHM Regression Loss. Details of the theorem can be viewed in the paper "Gradient Harmonized Single-stage Detector" https://arxiv.org/abs/

Grid R-CNN. This detector is the implementation of: - Grid R-CNN (https://arxiv.org/abs/1811.12030) - Grid R-CNN Plus: Faster and Better

Guided-Anchor-based head (GA-RPN, GA-RetinaNet, etc.). This GuidedAnchorHead will predict high-quality feature guided anchors and locations w

HRFPN (High Resolution Feature Pyrmamids) arXiv: https://arxiv.org/abs/1904.04514 Args: in_channels (list): number of channels for e