win10+英伟达3080显卡，训练数据报错。如果use_gpu=false，关闭gpu就正常的

执行命令：python tools/train.py -c configs/mot/fairmot/fairmot_dla34_30e_1088x608.yml -o use_gpu=true

信息提示如下

[11/18 16:16:14] ppdet.data.source.mot INFO: MOT dataset summary:
[11/18 16:16:14] ppdet.data.source.mot INFO: OrderedDict([('mot16.train', 55)])
[11/18 16:16:14] ppdet.data.source.mot INFO: Total images: 600
[11/18 16:16:14] ppdet.data.source.mot INFO: Image start index: OrderedDict([('mot16.train', 0)])
[11/18 16:16:14] ppdet.data.source.mot INFO: Total identities: 56
[11/18 16:16:14] ppdet.data.source.mot INFO: Identity start index: OrderedDict([('mot16.train', 0)])
W1118 16:16:15.058755 10392 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 8.6, Driver API Version: 11.6, Runtime API Version: 11.6
W1118 16:16:15.086740 10392 gpu_resources.cc:91] device: 0, cuDNN Version: 8.4.
[11/18 16:16:16] ppdet.utils.checkpoint INFO: The shape [14455] in pretrained weight reid.classifier.bias is unmatched with the shape [56] in model reid.classifier.bias. And the weight reid.classifier.bias will not be loaded
[11/18 16:16:16] ppdet.utils.checkpoint INFO: The shape [128, 14455] in pretrained weight reid.classifier.weight is unmatched with the shape [128, 56] in model reid.classifier.weight. And the weight reid.classifier.weight will not be loaded
[11/18 16:16:16] ppdet.utils.checkpoint INFO: Finish loading model weights: C:\Users\Administrator/.cache/paddle/weights\fairmot_dla34_crowdhuman_pretrained.pdparams
[11/18 16:16:26] ppdet.engine INFO: Epoch: [0] [ 0/100] learning_rate: 0.000100 loss: 9.432942 heatmap_loss: 1.201442 size_loss: 0.913217 offset_loss: 0.230315 det_loss: 1.523079 reid_loss: 4.227031 eta: 8:28:41 batch_cost: 10.1738 data_cost: 0.0000 ips: 0.5897 images/s
Traceback (most recent call last):
File "E:\PaddlePaddle\PaddleDetection\tools\train.py", line 177, in
main()
File "E:\PaddlePaddle\PaddleDetection\tools\train.py", line 173, in main
run(FLAGS, cfg)
File "E:\PaddlePaddle\PaddleDetection\tools\train.py", line 127, in run
trainer.train(FLAGS.eval)
File "E:\PaddlePaddle\PaddleDetection\ppdet\engine\trainer.py", line 454, in train
outputs = model(data)
File "D:\Python39\lib\site-packages\paddle\fluid\dygraph\layers.py", line 930, in __call__
return self._dygraph_call_func(*inputs, **kwargs)
File "D:\Python39\lib\site-packages\paddle\fluid\dygraph\layers.py", line 915, in _dygraph_call_func
outputs = self.forward(*inputs, **kwargs)
File "E:\PaddlePaddle\PaddleDetection\ppdet\modeling\architectures\meta_arch.py", line 59, in forward
out = self.get_loss()
File "E:\PaddlePaddle\PaddleDetection\ppdet\modeling\architectures\fairmot.py", line 99, in get_loss
loss = self._forward()
File "E:\PaddlePaddle\PaddleDetection\ppdet\modeling\architectures\fairmot.py", line 78, in _forward
reid_loss = self.reid(neck_feat, self.inputs)
File "D:\Python39\lib\site-packages\paddle\fluid\dygraph\layers.py", line 930, in __call__
return self._dygraph_call_func(*inputs, **kwargs)
File "D:\Python39\lib\site-packages\paddle\fluid\dygraph\layers.py", line 915, in _dygraph_call_func
outputs = self.forward(*inputs, **kwargs)
File "E:\PaddlePaddle\PaddleDetection\ppdet\modeling\reid\fairmot_embedding_head.py", line 115, in forward
loss = self.get_loss(reid_feat, inputs)
File "E:\PaddlePaddle\PaddleDetection\ppdet\modeling\reid\fairmot_embedding_head.py", line 163, in get_loss
loss = self.reid_loss(logit, target)
File "D:\Python39\lib\site-packages\paddle\fluid\dygraph\layers.py", line 930, in __call__
return self._dygraph_call_func(*inputs, **kwargs)
File "D:\Python39\lib\site-packages\paddle\fluid\dygraph\layers.py", line 915, in _dygraph_call_func
outputs = self.forward(*inputs, **kwargs)
File "D:\Python39\lib\site-packages\paddle\nn\layer\loss.py", line 397, in forward
ret = paddle.nn.functional.cross_entropy(
File "D:\Python39\lib\site-packages\paddle\nn\functional\loss.py", line 1722, in cross_entropy
raise ValueError("Target {} is out of upper bound.".format(
ValueError: Target 4547114506196783481 is out of upper bound.