This structure stores a list of boxes as a Nx4 torch.Tensor. It supports some common methods about boxes (`area`, `clip`, `nonempty`, etc

A wrapper around :class:`torch.nn.Conv2d` to support empty inputs and more features.

This class represents a list of instances in an image. It stores the attributes of instances (e.g., boxes, masks, labels, scores) as "fields"

This structure stores a list of rotated boxes as a Nx5 torch.Tensor. It supports some common methods about boxes (`area`, `clip`, `nonemp

A simple structure that contains basic shape specification about a tensor. It is often used as the auxiliary inputs/outputs of models, to

Visualizer that draws data about detection/segmentation on images. It contains methods like `draw_{text,box,circle,line,binary_mask,polygon}

Same as :class:`Checkpointer`, but is able to handle models in detectron & detectron2 model zoo, and apply conversions for legacy models.

This class stores the segmentation masks for all objects in one image, in the form of bitmaps. Attributes: tensor: bool Tensor o

A wrapper around :class:`torch.nn.ConvTranspose2d` to support zero-size tensor.

The user-facing class that provides metric storage functionalities. In the future we may add support for storing / logging other types of da

Structure that holds a list of images (of possibly varying sizes) as a single tensor. This works by padding the images to the same size,

Region of interest feature map pooler that supports pooling from one or more feature maps.

The box-to-box transform defined in R-CNN. The transformation is parameterized by 4 deltas: (dx, dy, dw, dh). The transformation scales the b

Evaluate AR for object proposals, AP for instance detection/segmentation, AP for keypoint detection outputs using COCO's metrics. See htt

Wrapper class to combine multiple :class:`DatasetEvaluator` instances. This class dispatches every evaluation call to all of its :class:

This class assigns to each predicted "element" (e.g., a box) a ground-truth element. Each predicted element will have exactly zero or one mat

Evaluate semantic segmentation results on cityscapes dataset using cityscapes API. Note: * It does not work in multi-machine distrib

Two linear layers for predicting Fast R-CNN outputs: 1. proposal-to-detection box regression deltas 2. classification scores

Write scalars to a json file. It saves scalars as one json per line (instead of a big json) for easy parsing. Examples parsing such a j

This class stores the segmentation masks for all objects in one image, in the form of polygons. Attributes: polygons: list[list[ndar

Computes and stores the average and current value

The box-to-box transform defined in Rotated R-CNN. The transformation is parameterized by 5 deltas: (dx, dy, dw, dh, da). The transformation

Evaluate instance segmentation results on cityscapes dataset using cityscapes API. Note: * It does not work in multi-machine distrib

Print **common** metrics to the terminal, including iteration time, ETA, memory, all losses, and the learning rate. It also applies smoot

Evaluate semantic segmentation metrics.

The op `SwapAlign2Nat` described in https://arxiv.org/abs/1903.12174. Given an input tensor that predicts masks of shape (N, C=VxU, H

The standard ResNet stem (layers before the first residual block).

Evaluate Panoptic Quality metrics on COCO using PanopticAPI. It saves panoptic segmentation prediction in `output_dir` It contains a syn

Make a detectron2 model traceable with caffe2 style. An original detectron2 model may not be traceable, or cannot be deployed directly a

Extracts data for CompoundVisualizer

Hard pixel mining with cross entropy loss, for semantic segmentation. This is used in TensorFlow DeepLab frameworks. Paper: DeeperLab: Si

Create a simple end-to-end predictor with the given config that runs on single device for a single input image. Compared to using the mo

Predictor output that contains segmentation and inner coordinates predictions for predefined body parts: * coarse segmentation, a tensor

Attribute: polygons (list[ndarray]): list[ndarray]: polygons for this mask. Each ndarray has format [x, y, x, y, ...]

Stores keypoint **annotation** data. GT Instances have a `gt_keypoints` property containing the x,y location and visibility flag of each keyp

Evaluate object proposal and instance detection/segmentation outputs using LVIS's metrics and evaluation API.

A wrapper around :class:`torch.nn.Linear` to support empty inputs and more features. Because of https://github.com/pytorch/pytorch/is

Base visualizer for matrix data

Evaluate Pascal VOC style AP for Pascal VOC dataset. It contains a synchronization, therefore has to be called from all ranks. Note that

Implement :paper:`ResNet`.

A simple trainer for the most common type of task: single-cost single-optimizer single-data-source iterative optimization. It assumes tha

Sobel layer.

Atrous Spatial Pyramid Pooling (ASPP).

Similar to nn.ParameterList, but for buffers

Representing a list of detectron2.structures.Boxes from minibatch, each box is represented by a 5d vector (batch index + 4 coordinates), or a

A wrapper around the traced model in caffe2's pb format. Examples: :: model = Caffe2Model.load_protobuf("dir/with/pb/files")

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

Compute anchors in the standard ways described in "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks".

DensePose results for chart-based methods represented by labels and quantized inner coordinates (U, V) of individual charts. Each chart is a

This module implements :paper:`FPN`. It creates pyramid features built on top of some input feature maps.

Tensor representation of a list of Instances object for a batch of images. When dealing with a batch of images with Caffe2 ops, a list of bb

Pooling layers for features from multiple depth.

Region Proposal Network, introduced by :paper:`Faster R-CNN`.

Two linear layers for predicting Rotated Fast R-CNN outputs.

Write all scalars to a tensorboard file.

Used to store data about detected objects in video frame, in order to transfer color to objects in the future frames. Attributes:

The alias method for sampling. From: https://hips.seas.harvard.edu/blog/2013/03/03/the-alias-method-efficient-sampling-with-many-discrete-outcome

Selector that accepts all entries

A predictor that runs the model asynchronously, possibly on >1 GPUs. Because rendering the visualization takes considerably amount of time,

Args: tensors_helper (SingleTensorsHelper) j_valid (:obj: `torch.Tensor`): uint8 tensor of size M containing 0 for po

Enum of different ways to represent a box.

The same as `fvcore.common.config.CfgNode`, but different in: 1. Use unsafe yaml loading by default. Note that this may lead to arbit

A color related data augmentation used in Single Shot Multibox Detector (SSD). Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy,

Contains mask GT and estimated data for proposals from multiple images:

Implement test-time augmentation for detection data. It is a callable which takes a dataset dict from a detection dataset, and returns a

A semantic segmentation head described in detail in the Panoptic Feature Pyramid Networks paper (https://arxiv.org/abs/1901.02446). It takes

The DeepLab ResNet stem (layers before the first residual block).