/Python/RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument

RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument

# 第二个类型是 torch.cuda.FloatTensor，这意味着它是已经移到 GPU 的张量。
# 它想获得类型为 torch.FloatTensor 的张量，但是没有 .cuda，因此该张量应该在 CPU 上。
# PyTorch 只能对位于相同设备上的张量进行运算，因此必须同时位于 CPU 或 GPU 上。如果你要在 GPU 
# 上运行网络，一定要使用 .to(device) 将模型和所有必要张量移到 GPU 上，其中 device 为 "cuda" 或 "cpu"。

device = 'cuda' if torch.cuda.is_available() else 'cpu'
model = model.to(device) # the same model.cuda()

for images, labels in trainloader:
	images, labels = images.to(device), labels.to(device)

Similar codes

1 vote198 views1 answer
'set' object is not reversible
Python
-2 votes173 views1 answer
3d game in python
Python
2 votes246 views2 answers
Print( n ) in python
Python
0 vote185 views1 answer
Pysft connection drop issue
Python
0 vote245 views1 answer
Seaborn boxplots shifted incorrectly along x-axis
Python
0 vote213 views1 answer
How to add new column in csv file using pandas
Python
0 vote221 views1 answer
Next function with inherited list python
Python
42 votes195 views6 answers
Python regex
Python
2 votes193 views1 answer
Is python easier than javascript
Python
0 vote190 views1 answer
Converting double spaces int single spaces python
Python