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 vote363 views1 answer
Percentage of null values for every variable in dataframe
Python
0 vote332 views1 answer
Matruzen rechner python
Python
9 votes329 views2 answers
Pygame.draw.rect()
Python
5 votes307 views1 answer
Snake nokia game project python
Python
79 votes353 views3 answers
Metronome
Python
1 vote340 views1 answer
What do i do if my dog eats paper
Python
0 vote351 views1 answer
WARNING: Ignoring invalid distribution c program files python39libsite-packages
Python
0 vote304 views1 answer
Find total no of true in a list in python
Python
4 votes318 views4 answers
Interface graphique sur python
Python
2 votes317 views1 answer
Pygame rect collisions
Python