YOLOv5训练时出现IndexError: index 3 is out of bounds for dimension 0 with size 2

Traceback (most recent call last):
  File "train.py", line 650, in <module>
    main(opt)
  File "train.py", line 546, in main
    train(opt.hyp, opt, device, callbacks)
  File "train.py", line 386, in train
    compute_loss=compute_loss)
  File "/home/user/anaconda3/envs/zx/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/user/ZX/yolov5-test/yolov5-v6.1-Tranformer/val.py", line 198, in run
    loss += compute_loss([x.float() for x in train_out], targets)[1]  # box, obj, cls
  File "/home/user/ZX/yolov5-test/yolov5-v6.1-Tranformer/utils/loss.py", line 120, in __call__
    tcls, tbox, indices, anchors = self.build_targets(p, targets)  # targets
  File "/home/user/ZX/yolov5-test/yolov5-v6.1-Tranformer/utils/loss.py", line 185, in build_targets
    gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]]  # xyxy gain
IndexError: index 3 is out of bounds for dimension 0 with size 2

请问如何解决，是哪里出现了问题？