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

30 votes111 views3 answers
For c in range python
Python
0 vote110 views1 answer
Hash python png
Python
1 vote99 views1 answer
Python name 'List' is not defined
Python
0 vote152 views1 answer
Python codes for counting the occurrence of a letters in dictionary excluding digits
Python
14 votes121 views1 answer
Python directory contains file
Python
3 votes120 views2 answers
Unix to date python
Python
0 vote108 views1 answer
How To Generate The Requirements Of Your Python Project Based On Your Imports
Python
1 vote112 views1 answer
Python list remove at index
Python
2 votes100 views2 answers
How to get percentage in python
Python
1 vote116 views1 answer
Multiprocessing join python
Python