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

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

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

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

InPlace Activated Batch Normalization with cross-GPU synchronization This assumes that it will be replicated across GPUs using the same mechanism

A wrapper around :class:`torch.nn.BatchNorm2d` to support zero-size tensor.

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

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

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,

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

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 object proposal, instance detection/segmentation, keypoint detection outputs using COCO's metrics and APIs.

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

This method returns a copy of this image, rotated the given number of degrees counter clockwise around its center.

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

Wrap a list to a torch Dataset. It produces elements of the list as data.

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

Evaluate instance segmentation results using cityscapes API. Note: * It does not work in multi-machine distributed training.

Evaluate semantic segmentation results using cityscapes API. Note: * It does not work in multi-machine distributed training.

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

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

Base visualizer for matrix data

Evaluate semantic segmentation

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

A customized version of `detectron2.data.DatasetMapper`

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

Map a function over the elements in a dataset. Args: dataset: a dataset where map function is applied. map_func: a callable

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

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

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

Print **common** metrics to the terminal, including iteration time, ETA, memory, all losses, and the learning rate. To print something d

Extracts data for CompoundVisualizer

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

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

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

A class that supports simple attribute setter/getter. It is intended for storing metadata of a dataset and make it accessible globally.

Evaluate Pascal VOC AP. It contains a synchronization, therefore has to be called from all ranks. Note that this is a rewrite of the off

Resize the image to a target size.

Batch data that have similar aspect ratio together. In this implementation, images whose aspect ratio < (or >) 1 will be batched together

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

Enum of different ways to represent a box.

Similar to nn.ParameterList, but for buffers

r""" Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).

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.

Implements data parallelism at the module level. This container parallelizes the application of the given module by splitting the input acros

A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by the model. This is the default call

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

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

Dense pose relative annotations that can be applied to any bounding box: x - normalized X coordinates [0, 255] of annotated points

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

A GeneralizedRCNN with test-time augmentation enabled. Its :meth:`__call__` method has the same interface as :meth:`GeneralizedRCNN.forward`.

Wraps another sampler to yield a mini-batch of indices. It enforces that the batch only contain elements from the same group. It also tri

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

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

Implement :paper:`ResNet`.

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

Consine annealing with warm up and restarts. Proposed in `SGDR: Stochastic Gradient Descent with Warm Restarts`.

A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by semantic segmentation models. The c

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:

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,

Output only the context features. Parameters: in_features / out_features: the channels of the input / output feature maps. dr