maozezhong

Have you solved this issue? @Colanim

@luckydog5 请问用上resnet效果怎么样？

@luckydog5 resize不收敛指的是？ 是resize到,600*800后不收敛了吗？

I solved the problem(at least it worked in my case) by changing source code in 1. lib/dataset/pascal_voc.py, about 175~178 lines, comment `-1` just like below: ``` x1 = float(bbox.find('xmin').text) #-...

I solved the problem(at least it worked in my case) by changing source code in 1. lib/dataset/pascal_voc.py, about 175~178 lines, comment `-1` just like below: ``` x1 = float(bbox.find('xmin').text) #-...

@mursalal，hello, Have you solved the problem?

I just find some pretrained model in follow link : 链接：https://pan.baidu.com/s/11bWI93-e5O3Rdzh7xwSvBA 密码：b38p Hope it helps

@jacktkk ， yes, I have tested it

@Asher-1 HI, 后续有提升吗？

@liuliu66 have you got the RetNet50 pre-trained model for faster-rcnn-ohem? hope for your reply~