/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

0 vote308 views1 answer
Convert from R to python
Python
2 votes335 views1 answer
Get stats from array python
Python
0 vote292 views1 answer
Cv2.cv2' has no attribute 'face_lbphfacerecognizer'
Python
3 votes286 views2 answers
Python get line of exception
Python
0 vote301 views1 answer
How to make a clicker game in python
Python
1 vote293 views1 answer
Get video length python
Python
1 vote371 views1 answer
Get active window title python
Python
1 vote282 views1 answer
Python export console output to file
Python
9 votes290 views4 answers
Fetch member by id discord.py
Python
0 vote295 views1 answer
Bold some letters of string in python
Python