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

2 votes211 views3 answers
Get webpage data as json python
Python
-1 vote184 views1 answer
Numpy make 2d array 1d
Python
0 vote209 views1 answer
Add new dimension
Python
0 vote190 views2 answers
How to set breakpoint in python pdb
Python
0 vote241 views1 answer
Parallel run of a function with multiple arguments partial
Python
21 votes303 views6 answers
Python avg
Python
8 votes252 views2 answers
Matplotlib x label rotation
Python
0 vote204 views1 answer
Python replace null in list
Python
2 votes254 views3 answers
Run flask in debug mode
Python Flask
0 vote209 views1 answer
Numpy multidimensional indexing
Python