Composes several augmentations together. Args: transforms (List[Transform]): list of transforms to compose. Example: >>> augme

Compute priorbox coordinates in center-offset form for each source feature map. Note: This 'layer' has changed between versions of the ori

Transforms a VOC annotation into a Tensor of bbox coords and label index Initilized with a dictionary lookup of classnames to indexes Argumen

VOC Detection Dataset Object input is image, target is annotation Arguments: root (string): filepath to VOCdevkit folder. im

Generate a convolutional LSTM cell

At test time, Detect is the final layer of SSD. Decode location preds, apply non-maximum suppression to location predictions based on conf

A simple timer.

A simple timer.

SSD Weighted Loss Function Compute Targets: 1) Produce Confidence Target Indices by matching ground truth boxes with (default)

Crop Arguments: img (Image): the image being input during training boxes (Tensor): the original bounding boxes in pt form

Single Shot Multibox Architecture The network is composed of a base VGG network followed by the added multibox conv layers. Each multibox lay

Transforms a tensorized image by swapping the channels in the order specified in the swap tuple. Args: swaps (int triple): final orde

Applies a lambda as a transform.