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

3 votes277 views2 answers
How to format a file in python
Python
1 vote317 views1 answer
Python ndarray string array into int
Python
0 vote297 views1 answer
Onetoone vs foreign key django
Python
0 vote301 views1 answer
Typecasting inpython
Python
0 vote281 views1 answer
Auto repost bot instagram python
Python
0 vote297 views1 answer
Python replace null in list
Python
0 vote288 views1 answer
Np.random.randint to generate -1 +1
Python
0 vote273 views1 answer
Discord.py - change the default help command
Python
0 vote326 views1 answer
Python mark function as no return
Python
0 vote289 views1 answer
Sort eigenvalues and eigenvectors python
Python