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 vote98 views1 answer
Python eliminar elementos de un diccionario
Python
2 votes102 views1 answer
Frequency count of values in pandas dataframe
Python
0 vote96 views1 answer
Sns histplot nan values
Python
0 vote98 views1 answer
How to get the memory location of a varible in python
Python
33 votes99 views3 answers
How to do an array in python
Python
0 vote101 views1 answer
Start loop at 1 python
Python
3 votes100 views2 answers
Pandas read excel with two headers
Python
0 vote108 views1 answer
Text splitter for nlp
Python
0 vote99 views2 answers
What does manage.py do
Python
7 votes61 views1 answer
Module namespace in python
Python