r"""A sequential container. Modules will be added to it in the order they are passed in the constructor. Alternatively, an ordered dict of mod

convert our dataset to Dataset class in pytorch.

Softmax loss function.

WARNING: this coder will return encoding with size=5, but takes size=7 boxes, anchors

Bootstrapped sigmoid cross entropy classification loss function. This loss uses a convex combination of training labels and the current model's p

Abstract base class for box coder.

An abstract class representing a pytorch-like Dataset. All other datasets should subclass it. All subclasses should override ``__len__``, that

Class to compute similarity based on Intersection over Area (IOA) metric. This class computes pairwise similarity between two BoxLists based on the

Pytorch edition of manual_stepping in tensorflow.

enum that indicate format of a bbox

Abstract base class for loss functions.

Pytorch edition of manual_stepping in tensorflow. DON'T SUPPORT PARAM GROUPS.

mixed precision optimizer wrapper. Arguments: optimizer (torch.optim.Optimizer): an instance of :class:`torch.optim.Optimizer

Class to compute similarity based on the squared distance metric. This class computes pairwise similarity between two BoxLists based on the negat

Abstract base class for 2d region similarity calculator.

Class to compute similarity based on Intersection over Union (IOU) metric. This class computes pairwise similarity between two BoxLists based on IO

Sigmoid focal cross entropy loss. Focal loss down-weights well classified examples and focusses on the hard examples. See https://arxiv.org/pdf/1

Softmax focal cross entropy loss. Focal loss down-weights well classified examples and focusses on the hard examples. See https://arxiv.org/pdf/1

L2 localization loss function with anchorwise output support. Loss[b,a] = .5 * ||weights[b,a] * (prediction[b,a,:] - target[b,a,:])||^2

Sigmoid cross entropy classification loss function.

Smooth L1 localization loss function. The smooth L1_loss is defined elementwise as .5 x^2 if |x|<1 and |x|-.5 otherwise, where x is the differenc