/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 vote140 views1 answer
Feature to determine image too dark opencv
Python
3 votes118 views2 answers
Isalnum python
Python
0 vote158 views1 answer
Import symspell
Python
0 vote130 views1 answer
Django jinja else if template tags
Python
2 votes128 views1 answer
Title() in python
Python
3 votes137 views1 answer
How to know all methods in a module in python
Python
0 vote134 views1 answer
Get category discord.py
Python
1 vote124 views2 answers
Convert 2d list to 1d python
Python
5 votes115 views1 answer
How to use path to change working directory in python
Python
59 votes124 views6 answers
Python replace character in string
Python