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 vote203 views1 answer
Sessions in flask
Python
4 votes309 views3 answers
E: Unable to locate package python3-pip
Python
0 vote186 views1 answer
Named tuple python iterate
Python
1 vote190 views1 answer
If a number times a number is true python
Python
0 vote186 views1 answer
Array with zeros python
Python
0 vote176 views2 answers
Python selenium switch to window
Python
0 vote205 views1 answer
Print all variables jupyter notebook
Python
2 votes195 views3 answers
Split string by length python
Python
0 vote212 views1 answer
Shuffle text lines python
Python
0 vote188 views1 answer
Datetime time set seconds
Python