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

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

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

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

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

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: 1. 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

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

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

Normlize image by given mean and std.

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.

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

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.

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:

Map a function over the elements in a dataset.

A simple trainer for the most common type of task: single-cost single-optimizer single-data-source iterative optimization, optionally usi

In training, we only care about the "infinite stream" of training data. So this sampler produces an infinite stream of indices and all wo

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

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

A model may take rich input/output format (e.g. dict or custom classes), but `torch.jit.trace` requires tuple of tensors as input/output.

A customized version of `detectron2.data.DatasetMapper`

Produce indices for inference across all workers. Inference needs to run on the __exact__ set of samples, therefore when the total number

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

Produce mask GT from DensePose predictions This sampler simply converts DensePose predictions to BitMasks that a contain a bool tensor of

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

Sampler implementation that converts predictions to GT using registered samplers for different fields of `Instances`.

Resize the image to a target size.

The standard ResNet stem (layers before the first residual block), with a conv, relu and max_pool.

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

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

A kxk depthwise convolution + a 1x1 convolution. In :paper:`xception`, norm & activation are applied on the second conv. :paper:`mobilen

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Feature fusion block.

A LRScheduler which uses fvcore :class:`ParamScheduler` to multiply the learning rate of each param in the optimizer. Every step, the lea

Selector that retains at most `k` random frames

Implement :paper:`ResNet`.

Implementation of a single process tensor storage which stores data in a file

A 2D upsampling layer with an optional convolution. Parameters: channels (`int`): number of channels in the inputs and output

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

Accumulates annotations by batches that correspond to objects detected on individual images. Can pack them together into single tensors.

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

Output head head consisting of 3 convolutional layers. It progressively halves the feature dimension and upsamples the predictions to the inp

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

Predictor output that contains embedding and coarse segmentation data: * embedding: float tensor of size [N, D, H, W], contains estimated em

Feature fusion block.

Transform that resizes images loaded from a dataset (BGR data in NCHW channel order, typically uint8) to a format ready to be consumed by

Base visualizer for matrix data

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

In PyTorch<=1.5, ``nn.SyncBatchNorm`` has incorrect gradient when the batch size on each worker is different. (e.g., when scale augmentat

Evaluate semantic segmentation metrics.

Implementation of a single process tensor storage which stores data in RAM

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

Convert an old indices-based (also called map-style) dataset to an iterable-style dataset.

Dataset that provides keyframes for a set of videos.

Add an initial warmup stage to another scheduler.

Atrous Spatial Pyramid Pooling (ASPP).

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

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

Extracts data for CompoundVisualizer

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

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

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

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

Samples DensePose data from DensePose predictions. Samples for each class are drawn using confidence value estimates.

Selector that retains at most `k` first frames

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

Interpolation module.

A standard keypoint head containing a series of 3x3 convs, followed by a transpose convolution and bilinear interpolation for upsampling.

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

Selector that retains at most `k` last frames from video data

Image to Patch Embedding Args: patch_size (int): Patch token size. Default: 4. in_chans (int): Number of input image channels. Def