苏北 陈晨
苏北 陈晨
I have the same problem, have you solved it？
我是用的是单机8卡，在general.py的output_to_target方法中 将这两句注释if isinstance(output, torch.Tensor): output = output.cpu().numpy() 并加上 output = [temp.cpu().numpy() for temp in output]
> 大佬们，评估时怎么显示每一个类别的ap啊？需要更改cocoeval.py吗？ 请问你解决了吗
I have the same problem. Have you solved it?
请问你解决了吗