This is a re-implemented and re-trained version of YOLO v2 object detection network trained with VOC2012 training dataset. Network weight pruning is applied to sparsify convolution layers (70% of network parameters are set to zeros).
Metric | Value |
---|---|
Mean Average Precision (mAP) | 62.9% |
Flops | 48.29Bn* |
Source framework | Tensorflow** |
Average Precision metric described in: Mark Everingham et al. "The PASCAL Visual Object Classes (VOC) Challenge".
Tested on VOC 2012 validation dataset.
num_anchors
, cls_reg_obj_params
, y_loc
, x_loc
], respectively.num_anchors
: number of anchor boxes, each spatial location specified by y_loc
and x_loc
has 5 anchors.cls_reg_obj_params
: parameters for classification and regression. The values are made up of the followings:y_loc
and x_loc
: spatial location of each grid.[*] Same as the original implementation.
[**] Other names and brands may be claimed as the property of others.