Zijian

Hi @Kenneth-Wong , I have modified the code and the results on my side is 72.1% with 416*416 input (trained with voc07+12). I found mAP blows up during training if...

After modified the code mentioned [here](https://github.com/longcw/yolo2-pytorch/issues/72), my mAP goes to 72.1% with 416*416 input.

@kk1153 I haven't trained models with only VOC07 dataset

I agree with @JesseYang 's points and in order to meet with the original code, I guess it should be _iou_mask[best_ious < cfg['iou_thresh']] = math.sqrt(0.5*cfg['noobject_scale']) (and as well as for...

I have the same confusion and hope someone can answer it. Thanks in advance.

@longcw Thank you for answering and thanks for the code!

I have met same problems. I guess the conversion code has not support 'ExpandBackward' currently.