/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

29 votes193 views4 answers
How to remove all characters from a string in python
Python
0 vote207 views1 answer
How to input sentence in python
Python
0 vote195 views1 answer
Ipython widget display
Python
0 vote201 views1 answer
Django only certain columns from database
Python
0 vote199 views1 answer
Rename dataframe index column pandas
Python
3 votes216 views5 answers
Python sha256 crypt decrypt
Python
3 votes258 views2 answers
Python check if list
Python
6 votes201 views3 answers
Django filter install
Python Django
0 vote206 views1 answer
Read data from excel file using openbyxl
Python
2 votes191 views1 answer
Python how to obfuscate code
Python