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

1 vote207 views1 answer
Escape string for html python
Python
1 vote233 views1 answer
Python new line character in string
Python
0 vote184 views1 answer
How ti maek a prinyt comnad i pyuthon
Python
8 votes186 views1 answer
Créer des variable dynamiques python
Python
-2 votes192 views2 answers
String pythhon
Python
0 vote186 views1 answer
Get the factorial of a number on python
Python
0 vote205 views1 answer
Boto3 cross region
Python
0 vote208 views1 answer
Check correlation of each column with the target in python
Python
9 votes198 views3 answers
Save model pickle
Python
1 vote190 views1 answer
Types of dict comprehension
Python