yolov5:训练分割模型时报错

Traceback (most recent call last):
  File "train.py", line 647, in <module>
    main(opt)
  File "train.py", line 536, in main
    train(opt.hyp, opt, device, callbacks)
  File "train.py", line 318, in train
    loss, loss_items = compute_loss(pred, targets.to(device))  # loss scaled by batch_size
  File "/home/ubuntu/yolov5/utils/loss.py", line 125, in __call__
    tcls, tbox, indices, anchors = self.build_targets(p, targets)  # targets
  File "/home/ubuntu/yolov5/utils/loss.py", line 198, in build_targets
    anchors, shape = self.anchors[i], p[i].shape
AttributeError: 'list' object has no attribute 'shape'

采用segment下的train.py进行训练，因为之外的train.py只能训练分类检测模型，对于用于分割的数据集无法识别，用于分割的数据集往往是一个物体多个点位，而用于分类检测的数据集只有一个矩形框的数据