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

5 votes107 views2 answers
Columns to dictionary pandas
Python
0 vote95 views1 answer
How to join models from another app
Python
1 vote103 views1 answer
How to create obtain any random 3 items of list in python
Python
0 vote98 views1 answer
Pandas dataframe hist title
Python
4 votes108 views1 answer
Return python meaning
Python
8 votes96 views3 answers
How to delete nan values in python
Python
2 votes98 views1 answer
Python checking if something is equal to NaN
Python
0 vote96 views2 answers
Online code formatter for pep8
Python
0 vote117 views1 answer
One small letter three big bodyguard
Python
3 votes101 views1 answer
Creating a virtual environment in python 3.8
Python