我的数据迭代器目前在CPU上运行，因为device=0参数已被弃用。但我需要它与模型的其余部分一起在GPU上运行。

这是我的代码:

pad_idx = TGT.vocab.stoi["<blank>"]model = make_model(len(SRC.vocab), len(TGT.vocab), N=6)model = model.to(device)criterion = LabelSmoothing(size=len(TGT.vocab), padding_idx=pad_idx, smoothing=0.1)criterion = criterion.to(device)BATCH_SIZE = 12000train_iter = MyIterator(train, device, batch_size=BATCH_SIZE,                        repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),                        batch_size_fn=batch_size_fn, train=True)valid_iter = MyIterator(val, device, batch_size=BATCH_SIZE,                        repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),                        batch_size_fn=batch_size_fn, train=False)#model_par = nn.DataParallel(model, device_ids=devices)

以上代码引发了以下错误:

The `device` argument should be set by using `torch.device` or passing a string as an argument. This behavior will be deprecated soon and currently defaults to cpu.The `device` argument should be set by using `torch.device` or passing a string as an argument. This behavior will be deprecated soon and currently defaults to cpu.

我尝试将'cuda'作为参数传入，而不是device=0，但收到了以下错误:

<ipython-input-50-da3b1f7ed907> in <module>()    10     train_iter = MyIterator(train, 'cuda', batch_size=BATCH_SIZE,    11                             repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),---> 12                             batch_size_fn=batch_size_fn, train=True)    13     valid_iter = MyIterator(val, 'cuda', batch_size=BATCH_SIZE,    14                             repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),TypeError: __init__() got multiple values for argument 'batch_size'

我也尝试将device作为参数传入。设备定义为device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

但收到了与上面相同的错误。

任何建议都将不胜感激，谢谢。

回答：

pad_idx = TGT.vocab.stoi["<blank>"]model = make_model(len(SRC.vocab), len(TGT.vocab), N=6)model = model.to(device)criterion = LabelSmoothing(size=len(TGT.vocab), padding_idx=pad_idx, smoothing=0.1)criterion = criterion.to(device)BATCH_SIZE = 12000train_iter = MyIterator(train, batch_size=BATCH_SIZE, device = torch.device('cuda'),                        repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),                        batch_size_fn=batch_size_fn, train=True)valid_iter = MyIterator(val, batch_size=BATCH_SIZE, device = torch.device('cuda'),                        repeat=False, sort_key=lambda x: (len(x.src), len(x.trg)),                        batch_size_fn=batch_size_fn, train=False)

经过多次尝试和错误后，我设法将device设置为device = torch.device('cuda')，而不是device=0