Pytorch cuda tensor in module

import torch
import torch.nn as nn

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.weight = torch.nn.Parameter(torch.zeros(2, 1))
        self.bias = torch.nn.Parameter(torch.zeros(1))
        self.register_buffer('a_constant_tensor', torch.tensor([0.5]))

    def forward(self, x):
        # linear regression completely from scratch,
        # using parameters created in __init__
        x = torch.mm(x, self.weight) + self.bias + self.a_constant_tensor
        return x


model = Model().cuda()

Source: discuss.pytorch.org

Similar codes

-1 vote215 views1 answer
How to delete django superuser
Python Django
2 votes317 views4 answers
Streamlit python install
Python
1 vote237 views1 answer
Printing with colors
Python
0 vote149 views4 answers
Python draw circle matplotlib
Python
0 vote172 views2 answers
Get random vowel python
Python
1 vote142 views2 answers
Incognito selenium
Python
0 vote161 views1 answer
Dict to csv keys as rows and subkey as columns in python
Python
0 vote153 views1 answer
How to download multiple googel images using python
Python
0 vote159 views2 answers
Morris Inorder Traversal python
Python
0 vote157 views1 answer
Discord.py cog classes
Python