一、问题描述

在跑pytorch代码时报错：

Expected all tensors to be on the same device, but found at least two devices, cuda:0

二、解决方案

判断参数数据是在cpu还是哪张gpu上：

import torch
import torch.nn as nn
 
# ----------- 判断模型是在CPU还是GPU上 ----------------------
 
model = nn.LSTM(input_size=10, hidden_size=4, num_layers=1, batch_first=True)
print(next(model.parameters()).device)  # 输出：cpu
 
model = model.cuda()
print(next(model.parameters()).device)  # 输出：cuda:0
 
model = model.cpu()
print(next(model.parameters()).device)  # 输出：cpu
 
# ----------- 判断数据是在CPU还是GPU上 ----------------------
 
data = torch.ones([2, 3])
print(data.device)  # 输出：cpu
 
data = data.cuda()
print(data.device)  # 输出：cuda:0
 
data = data.cpu()
print(data.device)  # 输出：cpu

查看模型的参数是在哪里（其实也可以直接data.is_cuda）：

model = nn.LSTM(input_size=10, hidden_size=4, num_layers=1, batch_first=True)
print(next(model.parameters()).device)  

（1）可能是模型没有移动到和数据相同的device上：model.to(device)
（2）可能是input和参数没有在相同device上，如下类似的操作即可：

device = torch.device("cuda:0" if (torch.cuda.is_available() and ngpu > 0) else "cpu")
data.to(device)