Pytorch 嵌入 RuntimeError：预期为 torch.LongTensor 类型的对象，但为参数 #3 'index' 找到了类型 torch.cuda.LongTensor

Question

我收到这个错误提示

RuntimeError: Expected object of type torch.LongTensor but found type torch.cuda.LongTensor for argument #3 'index'

但是argument #3 "index" 是什么意思？我在torch.embedding 中找不到“index”参数（此处来源：https://pytorch.org/docs/stable/_modules/torch/nn/modules/sparse.html#Embedding） 好像我正在传递嵌入错误的参数。

我什至像下面这样更改了输入的数据类型，但错误仍然存​​在。

batch['doc_tok'] = batch['doc_tok'].long()
batch['query_tok'] = batch['query_tok'].long()

任何评论（即使很短！）或仅列出要查看的关键字都将受到高度赞赏！

---

这是一个完整的回溯。

Traceback (most recent call last):
  File "train_v2.py", line 110, in <module>
    main()
  File "train_v2.py", line 81, in main
    model.update(batch)
  File "/home/aerin/Desktop/squad_vteam/src/model.py", line 129, in update
    loss_adv = self.adversarial_loss(batch, loss, self.network.lexicon_encoder.embedding.weight, y)
  File "/home/aerin/Desktop/squad_vteam/src/model.py", line 104, in adversarial_loss
    start, end, _ = self.network(batch)
  File "/home/aerin/anaconda3/envs/san/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/aerin/Desktop/squad_vteam/src/dreader.py", line 78, in forward
    doc_mask, query_mask = self.lexicon_encoder(batch)
  File "/home/aerin/anaconda3/envs/san/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/aerin/Desktop/squad_vteam/src/encoder.py", line 116, in forward
    doc_emb, query_emb = emb(doc_tok), emb(query_tok)
  File "/home/aerin/anaconda3/envs/san/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/aerin/anaconda3/envs/san/lib/python3.6/site-packages/torch/nn/modules/sparse.py", line 108, in forward
    self.norm_type, self.scale_grad_by_freq, self.sparse)
  File "/home/aerin/anaconda3/envs/san/lib/python3.6/site-packages/torch/nn/functional.py", line 1076, in embedding
    return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected object of type torch.LongTensor but found type torch.cuda.LongTensor for argument #3 'index'

---

更新：我什至将整个 model.network 发送到 cpu，但仍然遇到同样的错误。

batch['doc_tok']=batch['doc_tok'].long().cpu()
batch['query_tok']=batch['query_tok'].long().cpu()
self.network.cpu()

print(batch['doc_tok'].dtype,  batch['query_tok'].dtype) # They are both torch.int64 torch.int64

start, end, _ = self.network(batch)

在这一点上，我怀疑这可能是一个错误......

model.py 代码：https://github.com/byorxyz/san_mrc/blob/master/src/model.py

网络定义：https://github.com/byorxyz/san_mrc/blob/master/src/dreader.py

Answer 1

在我看来，您的输入/目标张量（batch['doc_tok'] 等）和您的网络及其变量（我相信 index 是 Embedding 层的内部张量）在不同的设备上（CPU 用于你的数据，你的模型的 GPU？）。

如果您希望一切都在 GPU 上运行，您需要同时满足以下条件：

• 在那里加载您的数据，例如batch['doc_tok'].cuda()
• 在那里加载您的模型，例如model.network.cuda()

如果你想在 CPU 上运行，也一样，替换为 .cpu()。

Answer 2

试试这个：

batch['doc_tok']=batch['doc_tok'].long().cpu()
batch['query_tok']=batch['query_tok'].long().cpu()