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

1 vote109 views1 answer
Timedelta to float
Python
0 vote157 views1 answer
Rdflib check if graph is empty
Python
0 vote114 views1 answer
Same elements of two sets in python
Python
1 vote102 views1 answer
Find all text in site python
Python
7 votes137 views4 answers
Modules in python
Python
236 votes334 views6 answers
Import random in python
Python
4 votes113 views1 answer
Change default option optionmenu tkinter
Python
0 vote115 views1 answer
Difference between calling a function and referencing a function python
Python
0 vote102 views1 answer
Checking if a string is in alphabetical order in python
Python
0 vote98 views1 answer
Django iterating through objects
Python Django