An abstract Dataset class wrapped around Pytorch Dataset class.

Placeholder for 'route' and 'shortcut' layers

A data iterator that will never stop producing data

Bounding box dataset for PASCAL `VOC`_. .. _`VOC`: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/ The index corresponds to each image.

docstring for GlobalModel

Assign the ground truth bounding boxes to anchors. Assigns the ground truth bounding boxes to anchors for training Region Proposal Networks i

YOLOv3 object detection model

wrapper for conveniently training. return losses The losses include: * :obj:`rpn_loc_loss`: The localization loss for \ Region Propo

Faster R-CNN based on VGG-16. For descriptions on the interface of this model, please refer to :class:`model.faster_rcnn.FasterRCNN`. Arg

Proposal regions are generated by calling this object. The :meth:`__call__` of this object outputs object detection proposals by applying est

Assign ground truth bounding boxes to given RoIs. The :meth:`__call__` of this class generates training targets for each object proposal.

Region Proposal Network introduced in Faster R-CNN. This is Region Proposal Network introduced in Faster R-CNN [#]_. This takes features extr

nn.Upsample is deprecated

Faster R-CNN Head for VGG-16 based implementation. This class is used as a head for Faster R-CNN. This outputs class-wise localizations and cl

wrapper for visdom you can still access naive visdom function by self.line, self.scater,self._send,etc. due to the implementation of

Detection layer