YOLOv5训练模型求助帖

有没有大神帮我看一下，这个错误到底怎么修改啊。在用yolov5训练模型的时候，一直报错，然后修改了dataloaders.py，loss.py等，会不会越改越乱啊，我看网上都没有说训练的时候要修改这些文件呜呜呜。

目前的一个错误是这样的：

Traceback (most recent call last):
  File "D:\yolov5-7.0\train.py", line 634, in <module>
    main(opt)
  File "D:\yolov5-7.0\train.py", line 528, in main
    train(opt.hyp, opt, device, callbacks)
  File "D:\yolov5-7.0\train.py", line 351, in train
    results, maps, _ = validate.run(data_dict,
  File "D:\anaconda\envs\yolov5\lib\site-packages\torch\autograd\grad_mode.py", line 28, in decorate_context
    return func(*args, **kwargs)
  File "D:\yolov5-7.0\val.py", line 213, in run
    loss_part = compute_loss(train_out, targets)
  File "D:\yolov5-7.0\utils\loss.py", line 106, in __call__
    obji = self.BCEobj(pi[..., 4], tobj_clone)
  File "D:\anaconda\envs\yolov5\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\anaconda\envs\yolov5\lib\site-packages\torch\nn\modules\loss.py", line 713, in forward
    return F.binary_cross_entropy_with_logits(input, target,
  File "D:\anaconda\envs\yolov5\lib\site-packages\torch\nn\functional.py", line 2960, in binary_cross_entropy_with_logits
    return torch.binary_cross_entropy_with_logits(input, target, weight, pos_weight, reduction_enum)
RuntimeError: Inplace update to inference tensor outside InferenceMode is not allowed.You can make a clone to get a normal tensor before doing inplace update.See https://github.com/pytorch/rfcs/pull/17 for more details.

进程已结束,退出代码1
 

非常感谢大家百忙之中给我看看，能不能给我个修改建议啊！