多GPU训练

[starsky68]

在使用torch.nn.DataParallel多gpu训练的时候，train阶段没问题，val阶段报错。
raceback (most recent call last):
File "train.py", line 347, in
train()
File "train.py", line 315, in train
evaluator.evaluate(model)
File "/home/11/CenterNet-Lite-master/utils/cocoapi_evaluator.py", line 196, in evaluate
outputs = model(x)
File "/home/11/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/11/.local/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 161, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/home/11/.local/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 171, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/home/11/.local/lib/python3.8/site-packages/torch/nn/parallel/parallel_apply.py", line 86, in parallel_apply
output.reraise()
File "/home/11/.local/lib/python3.8/site-packages/torch/_utils.py", line 428, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in replica 0 on device 0.
Original Traceback (most recent call last):
File "/home/11/.local/lib/python3.8/site-packages/torch/nn/parallel/parallel_apply.py", line 61, in _worker
output = module(*input, **kwargs)
File "/home/11/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/11/CenterNet-Lite-master/models/centernet.py", line 215, in forward
cls_loss, txty_loss, twth_loss, total_loss = tools.loss(pred_cls=cls_pred,
File "/home/11/CenterNet-Lite-master/tools.py", line 160, in loss
gt_cls = label[:, :, :num_classes].float()
TypeError: 'NoneType' object is not subscriptable