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

3 votes211 views4 answers
Generate fibonacci series in python
Python
1 vote176 views1 answer
Transparancy argument pyplot
Python
0 vote165 views1 answer
Repeat printing rows excel using python whenever i run the script
Python
0 vote189 views1 answer
Dataframe fill none
Python
13 votes179 views5 answers
Converting numpy array to dataframe
Python
0 vote231 views1 answer
Codeforces 677a solution
Python
10 votes167 views3 answers
How to make a rect in pygame
Python
-1 vote183 views3 answers
Play Video in Google Colab
Python
2 votes171 views2 answers
Get a liste from a txt file python
Python
3 votes194 views1 answer
Python docstring
Python