caffe-yolo
caffe-yolo copied to clipboard
The performance of this one vs the darknet version
Hi: Guys, I have converted the weightings from darknet version and run it on caffe. The performance is quite bad. The mAP is lower than 0.5 Can anyone report their AP of each class in the version?
@AlexofNTHU I trained this caffe-yolo model on VOC dataset, after 200K iters, the mAP is 0.58 on VOC07 ? why the mAP is lower on the darkent ?