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 vote346 views1 answer
Menubar pyqt
Python
0 vote351 views3 answers
Tower of Hanoi
Python
0 vote337 views1 answer
Spark.read.load
Python
0 vote366 views1 answer
Where to import messages in django
Python Django
2 votes394 views2 answers
Localize timezone python
Python
0 vote353 views1 answer
Pdfkit supress output
Python
12 votes348 views6 answers
Python check if nan
Python
2 votes334 views2 answers
Trim starting space python
Python
0 vote352 views1 answer
Python beautifulsoup xpath
Python
23 votes334 views4 answers
Python delete white spaces
Python