当我启用了SegHead结构后，就发生了报错。

[FriendChi]

Traceback (most recent call last): File "train.py", line 142, in train(net, train_loader, loss_dict, optimizer, scheduler,logger, epoch, metric_dict, cfg.dataset) File "train.py", line 30, in train loss = calc_loss(loss_dict, results, logger, global_step, epoch) File "/root/Ultra-Fast-Lane-Detection-v2-master/utils/common.py", line 274, in calc_loss loss_cur = loss_dict['op']i File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/loss.py", line 1174, in forward return F.cross_entropy(input, target, weight=self.weight, File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/functional.py", line 3029, in cross_entropy return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing) RuntimeError: only batches of spatial targets supported (3D tensors) but got targets of size: : [32, 3, 320, 800]

经过我的检查我发现，模型会直接返回seghead结构的输出，然后将其与其的标签放入cross_entropy_loss函数，但关键是cross_entropy_loss函数要求的输入是batch_size*C，两者的形状不符所以发生了错误，但我想不应该是你的代码发生了错误，所以问题出在哪呢

[Yysheepsheep]

你好 想问一下问题解决了嘛

[FriendChi]

你好 想问一下问题解决了嘛

v2版本没有使用seghead结构，这可能是上一版本的遗留代码，不要启动它