This class represents a set of bounding boxes. The bounding boxes are represented as a Nx4 Tensor. In order to uniquely determine the bou

This class encodes and decodes a set of bounding boxes into the representation used for training the regressors.

Wraps another sampler to yield a mini-batch of indices. It enforces that elements from the same group should appear in groups of batch_size.

BatchNorm2d where the batch statistics and the affine parameters are fixed

This class holds a set of polygons that represents a single instance of an object mask. The object can be represented as a set of polygon

This class stores the segmentations for all objects in the image

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

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,

Pooler for Detection with or without FPN. It currently hard-code ROIAlign in the implementation, but that can be made more generic later

For a set of image sizes and feature maps, computes a set of anchors

This class samples batches, ensuring that they contain a fixed proportion of positives

This class is unfinished and not meant for use yet It is supposed to contain the mask for an object as a 2d tensor

Projects a set of masks in an image on the locations specified by the bounding boxes

From a list of samples from the dataset, returns the batched images and targets. This should be passed to the DataLoader

Similar to nn.ParameterList, but for buffers

Combines a set of individual heads (for box prediction or masks) into a single head.

Computes the loss for Faster R-CNN. Also supports FPN

Wraps a BatchSampler, resampling from it until a specified number of iterations have been sampled

Determine which FPN level each RoI in a set of RoIs should map to based on the heuristic in the FPN paper.

From the results of the CNN, post process the masks by taking the mask corresponding to the class with max probability (which are of fixe

From a set of classification scores, box regression and proposals, computes the post-processed boxes, and applies NMS to obtain the final

Generic Box Head class.

Adds a simple RPN Head with classification and regression heads

This class computes the RPN loss.

Module for RPN computation. Takes feature maps from the backbone and RPN proposals and losses. Works for both FPN and non-FPN.

Performs post-processing on the outputs of the RPN boxes, before feeding the proposals to the heads

Performs post-processing on the outputs of the RetinaNet boxes. This is only used in the testing.

Adds a RetinNet head with classification and regression heads

This class computes the RetinaNet loss.

Module for RetinaNet computation. Takes feature maps from the backbone and RPN proposals and losses.

Performs post-processing on the outputs of the RetinaNet boxes. This is only used in the testing.

Same as torch.utils.data.dataset.ConcatDataset, but exposes an extra method for querying the sizes of the image

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

Module that adds FPN on top of a list of feature maps. The feature maps are currently supposed to be in increasing depth order, and must

Heads for FPN for classification

Main class for Generalized R-CNN. Currently supports boxes and masks. It consists of three main parts: - backbone = rpn - heads:

This module is used in RetinaNet to generate extra layers, P6 and P7.

From the results of the CNN, post process the results so that the masks are pasted in the image, and additionally convert the results to

Heads for FPN for classification

Main class for RetinaNet It consists of three main parts: - backbone - bbox_heads: BBox prediction. - Mask_heads:

Track a series of values and provide access to smoothed values over a window or the global series average.