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 vote202 views1 answer
Python word cloud
Python
2 votes150 views1 answer
Raise RuntimeError("populate() isn't reentrant")
Python
1 vote160 views2 answers
Convert string to utf8 python
Python
-1 vote177 views1 answer
AI code in Pythin
Python
0 vote262 views1 answer
Relative path django
Python Django
-1 vote144 views1 answer
Python object is not subscriptable
Python
1 vote160 views1 answer
How to make player quit in python
Python
0 vote228 views1 answer
Python delete header row
Python
5 votes218 views4 answers
OSError: [E050] Can't find model 'en'. It doesn't seem to be a shortcut link, a Python package or a valid path to a data directory.
Python
1 vote204 views1 answer
How to add decorators with class in django
Python Django