训练报错了，换了一个一样数据就错了，根据提示找不到问题，请教一下大佬,

[qiyuefun]

Traceback (most recent call last): File "train.py", line 187, in train(net, train_loader, loss_dict, optimizer, scheduler,logger, epoch, metric_dict, cfg.use_aux) File "train.py", line 99, in train loss = calc_loss(loss_dict, results, logger, global_step) File "train.py", line 62, in calc_loss loss_cur = loss_dict['op']i File "/home/zkys/anaconda3/envs/ldhtorch/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/zkys/anaconda3/envs/ldhtorch/lib/python3.8/site-packages/torch/nn/modules/loss.py", line 1150, in forward return F.cross_entropy(input, target, weight=self.weight, File "/home/zkys/anaconda3/envs/ldhtorch/lib/python3.8/site-packages/torch/nn/functional.py", line 2846, 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: : [16, 36, 100, 3]

[qiyuefun]

python train config/culone.py 就报错了

[xings-sdnu]

把--use_aux改为False就可以了：parser.add_argument('--use_aux', default='False', type=str2bool)