/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 vote266 views1 answer
Remove all files in a directory mac
Python
6 votes232 views2 answers
List of characters to string python
Python
0 vote247 views1 answer
The process of delivery of any desisered data
Python
0 vote269 views1 answer
How to import date python
Python
3 votes279 views1 answer
Python for data analysis
Python
1 vote226 views2 answers
Delete a key and value from dict python
Python
1 vote278 views1 answer
Constructor python variables
Python
7 votes248 views1 answer
// meaning in python
Python
12 votes291 views4 answers
How to know if a input is a interger in python
Python
10 votes273 views1 answer
How to add legend to python plot
Python