YOLOv2 icon indicating copy to clipboard operation
YOLOv2 copied to clipboard

Published 20 hours ago • verified publisher icon leetenki

Hove you tried training with VOC dataset?

Open wkentaro opened this issue 8 years ago • 4 comments

I'd like to know if the accuracy was also reproduced. Have you tried this?

wkentaro avatar Feb 19 '17 16:02 wkentaro

I've modified the code and tried testing performance on VOC2007-test, but the mAP was 74.2 on 416x416 input, 0.45 nms thresh, 0.005 detection thresh (all parameters are written in the original paper. Original mAP was 76.8). I can't figure out what's wrong, do you have any suggestions? https://github.com/naoto0804/YOLOv2/blob/voc/test.py

naoto0804 avatar Feb 28 '17 02:02 naoto0804

@naoto0804 Thank you for sharing the info. Currently I'm wondering why the pad parameters are different among Chainer/darknet implementations. In Chainer one it has pad=0: https://github.com/leetenki/YOLOv2/blob/master/yolov2.py#L28, but darknet has all pad=1.

wkentaro avatar Feb 28 '17 04:02 wkentaro

@naoto0804 as in you tried to train using this code or simply load in the weights from darknet?

Breakend avatar Apr 14 '17 20:04 Breakend

@Breakend Sorry for my extremely late reply! I tried to simply load the weights from darknet and tested.

naoto0804 avatar Dec 29 '17 15:12 naoto0804