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

0 vote133 views1 answer
Undef variable
Python
0 vote130 views1 answer
Audio streaming python
Python
4 votes137 views3 answers
Python get os
Python
1 vote133 views2 answers
Python - remove exta space in column
Python
1 vote130 views1 answer
Python cmath constants
Python
0 vote130 views1 answer
Accumulator programming python
Python
0 vote127 views2 answers
Program to replace lower-case characters with upper-case and vice versa in python
Python
23 votes128 views2 answers
Django rest
Python
0 vote127 views1 answer
Ldap python how to print entries
Python
1 vote157 views1 answer
How to loop over day name in python
Python