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

4 votes311 views2 answers
Online pygame compiler with sprites
Python
0 vote226 views1 answer
Split string with first numerical value in python
Python
1 vote263 views1 answer
Discord.py "NameError: name 'has_permissions' is not defined"
Python
1 vote269 views1 answer
Enumerate string pythonm
Python
0 vote353 views1 answer
RuntimeError: cannot open featureclass in python
Python
3 votes274 views6 answers
Python variable
Python
0 vote277 views1 answer
Python linter
Python
0 vote292 views2 answers
Diagonal difference hackerrank solution in python
Python
21 votes277 views1 answer
Jupyter ignore warnings
Python
10 votes313 views3 answers
Accessing element from csv file in python
Python