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

26 votes312 views4 answers
Python global variables
Python
2 votes303 views1 answer
Flask minimul app
Python Flask
5 votes280 views3 answers
Converting string array to int array python
Python
-1 vote270 views2 answers
Coin flip numpy
Python
1 vote266 views1 answer
Get list of objects in group godot
Python
0 vote236 views1 answer
Change state of tkintr btn
Python
2 votes260 views2 answers
First day of the month python
Python
1 vote314 views1 answer
Django foreign key error Cannot assign must be a instance
Python Django
4 votes250 views3 answers
How to make python speak
Python
0 vote275 views1 answer
Image resolution extracting python
Python