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 vote208 views1 answer
Set size of button tkinter
Python
0 vote194 views2 answers
Pandas replace non numeric values with 0?
Python
0 vote163 views1 answer
Ec2 upgrade python 3.7 to 3.8
Python
0 vote166 views1 answer
Redis in django channels
Python
0 vote169 views1 answer
Btr
Python
0 vote168 views1 answer
Too many python versions pip package location
Python
4 votes167 views4 answers
Filter django or
Python
0 vote184 views1 answer
Dynamic printing
Python
1 vote180 views1 answer
Markers seaborn
Python
14 votes223 views5 answers
Remove extra spaces python
Python