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

4 votes192 views2 answers
Flask arguments in url
Python
0 vote2.6K views1 answer
Tqdm continues afer break
Python
0 vote172 views1 answer
Lims
Python
3 votes177 views2 answers
Find location of max value in python list
Python
3 votes201 views10 answers
Rick roll
Python
24 votes193 views1 answer
Print type(x) in python
Python
1 vote236 views1 answer
Query with condition django
Python Django
0 vote223 views3 answers
How to install pandas in python by git
Python
3 votes180 views1 answer
Make a window tkinter
Python
0 vote174 views1 answer
Openai python
Python