Very simple multi-layer perceptron (also called FFN)

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

ResNet backbone with frozen BatchNorm.

This is the DETR module that performs object detection

Gaussian blur augmentation in SimCLR https://arxiv.org/abs/2002.05709

This class computes an assignment between the targets and the predictions of the network For efficiency reasons, the targets don't include the no

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

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 t

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

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

SelfDet is a dataset class which implements random query patch detection. It randomly crops patches as queries from the given image with the

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

This is the UPDETR module for pre-training. UPDETR inherits from DETR with same backbone,transformer,object queries and etc.

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

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