This is a re-implemented and re-trained version of tiny YOLO v2 object detection network trained with VOC2012 training dataset. Network weight pruning is applied to sparsify convolution layers (60% of network parameters are set to zeros).
|Mean Average Precision (mAP)||35.32%|
Average Precision metric described in: Mark Everingham et al. "The PASCAL Visual Object Classes (VOC) Challenge".
Tested on VOC 2012 validation dataset.
num_anchors: number of anchor boxes, each spatial location specified by
x_lochas 5 anchors.
cls_reg_obj_params: parameters for classification and regression. The values are made up of the followings:
x_loc: spatial location of each grid.
[*] Same as the original implementation.
[**] Other names and brands may be claimed as the property of others.