Python RuntimeError：应为后端CPU的对象，但为参数#3'获取了后端CUDA；指数'；

我正在用BERT进行论证挖掘实验，并尝试识别论证成分（生物分类任务）。我密切关注本文中的代码，但对其进行了修改以适合我的数据。我在colab上运行代码（硬件加速器设置为GPU）

有人知道我的问题的解决办法吗？提前谢谢

epochs = 5
max_grad_norm = 1.0

for _ in trange(epochs, desc="Epoch"):
    # TRAIN loop
    model.train()
    tr_loss = 0
    nb_tr_examples, nb_tr_steps = 0, 0
    for step, batch in enumerate(train_dataloader):
        # add batch to gpu
        batch = tuple(t.to(device) for t in batch)
        b_input_ids, b_input_mask, b_labels = batch
        # forward pass
        loss = model(b_input_ids, token_type_ids=None, attention_mask=b_input_mask, labels=b_labels)
        # backward pass
        loss.backward()
        # track train loss
        tr_loss += loss.item()
        nb_tr_examples += b_input_ids.size(0)
        nb_tr_steps += 1
        # gradient clipping
        torch.nn.utils.clip_grad_norm_(parameters=model.parameters(), max_norm=max_grad_norm)
        # update parameters
        optimizer.step()
        model.zero_grad()
    # print train loss per epoch
    print("Train loss: {}".format(tr_loss/nb_tr_steps))
    # VALIDATION on validation set
    model.eval()
    eval_loss, eval_accuracy = 0, 0
    nb_eval_steps, nb_eval_examples = 0, 0
    predictions , true_labels = [], []
    for batch in valid_dataloader:
        batch = tuple(t.to(device) for t in batch)
        b_input_ids, b_input_mask, b_labels = batch

        with torch.no_grad():
            tmp_eval_loss = model(b_input_ids, token_type_ids=None,
                                  attention_mask=b_input_mask, labels=b_labels)
            logits = model(b_input_ids, token_type_ids=None,
                           attention_mask=b_input_mask)
        logits = logits.detach().cpu().numpy()
        label_ids = b_labels.to('cpu').numpy()
        predictions.extend([list(p) for p in np.argmax(logits, axis=2)])
        true_labels.append(label_ids)

        tmp_eval_accuracy = flat_accuracy(logits, label_ids)

        eval_loss += tmp_eval_loss.mean().item()
        eval_accuracy += tmp_eval_accuracy

        nb_eval_examples += b_input_ids.size(0)
        nb_eval_steps += 1
    eval_loss = eval_loss/nb_eval_steps
    print("Validation loss: {}".format(eval_loss))
    print("Validation Accuracy: {}".format(eval_accuracy/nb_eval_steps))
    pred_tags = [tags_vals[p_i] for p in predictions for p_i in p]
    valid_tags = [tags_vals[l_ii] for l in true_labels for l_i in l for l_ii in l_i]
    print("F1-Score: {}".format(f1_score(pred_tags, valid_tags)))

虽然我严格遵循了原始代码，但它似乎对我不起作用，我一直在犯这个错误

RuntimeError                              Traceback (most recent call last)
<ipython-input-45-aa659bbf8fac> in <module>()
     12 
     13         # forward pass
---> 14         loss = model(b_input_ids, token_type_ids=None, attention_mask=b_input_mask, labels=b_labels)
     15         # backward pass
     16         loss.backward()

8 frames
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
   1465         # remove once script supports set_grad_enabled
   1466         _no_grad_embedding_renorm_(weight, input, max_norm, norm_type)
-> 1467     return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
   1468 
   1469 

RuntimeError: Expected object of backend CPU but got backend CUDA for argument #3 'index'

运行时错误回溯（最近一次调用）
在（）
12
13#向前传球
--->14损失=模型（b_输入_ID，令牌类型_ID=无，注意_掩码=b_输入_掩码，标签=b_标签）
15#向后传球
16.损失向后（）
8帧
/嵌入中的usr/local/lib/python3.6/dist-packages/torch/nn/functional.py（输入、重量、填充idx、最大规范、规范类型、比例梯度、频率、稀疏）
1465#一旦脚本支持set#grad#启用，则删除
1466(重量,输入,最大范数,范数类型)
->1467返回火炬。嵌入（重量、输入、填充idx、比例、梯度、稀疏）
1468
1469
RuntimeError:应为后端CPU的对象，但为参数#3“index”获取了后端CUDA

解决方案：

---

将model=model.to（device）加上将批处理大小从32减少到4，允许程序在没有任何运行时错误的情况下运行

在代码前面设置model.to（device）并让use知道。这将返回另一个运行时错误：RuntimeError:CUDA内存不足。尝试分配192.00 MiB（GPU 0；11.17 GiB总容量；10.66 GiB已分配；139.81 MiB空闲；54.26 MiB缓存）重新启动内核，然后重试，所有内容都应转到device=cuda或device=cpu