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

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

A simple timer.

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

Defines the transformations that should be applied to test PIL image for input into the network dimension -> tensorize -> color adj

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

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

Params for coco evaluation api

RFB Net for object detection The network is based on the SSD architecture. Each multibox layer branches into 1) conv2d for class conf

VOC Segmentation Dataset Object input and target are both images NOTE: need to address https://github.com/pytorch/vision/issues/9 Argume

--- Type declarations ---*/