Very simple multi-layer perceptron (also called FFN)

This class converts the output of the model to the final panoptic result, in the format expected by the coco panoptic API

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

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

ResNet backbone with frozen BatchNorm.

Inherit official COCO class in order to parse the annotations of bbox- related video tasks. Args: annotation_file (str): location o

This is the Deformable DETR module that performs object detection

This is the Deformable DETR module that performs object detection

This class computes an assignment between the targets and the predictions of the network For efficiency reasons, the targets don't include the

This is a 2D attention module, which only returns the attention softmax (no multiplication by value)

Very simple multi-layer perceptron (also called FFN)

Simple convolutional head, using group norm. Upsampling is done using a FPN approach

Absolute pos embedding, learned.

This is a more standard version of the position embedding, very similar to the one used by the Attention is all you need paper, generalized

This module converts the model's output into the format expected by the coco api

This module converts the model's output into the format expected by the coco api

This class computes the loss for DETR. The process happens in two steps: 1) we compute hungarian assignment between ground truth boxes

This class computes the loss for DETR. The process happens in two steps: 1) we compute hungarian assignment between ground truth boxes

`MS Coco Detection <http://mscoco.org/dataset/#detections-challenge2016>`_ Dataset. Args: root (string): Root directory where images are

Inherit official COCO class in order to parse the annotations of bbox- related video tasks. Args: annotation_file (str): location

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

BatchNorm2d where the batch statistics and the affine parameters are fixed. Copy-paste from torchvision.misc.ops with added eps before rq

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

Randomly selects between transforms1 and transforms2, with probability p for transforms1 and (1 - p) for transforms2

Randomly selects between transforms1 and transforms2, with probability p for transforms1 and (1 - p) for transforms2