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 vote229 views1 answer
Discord py server.channels
Python
0 vote230 views1 answer
Munshi premchand
Python
0 vote238 views1 answer
How to print correlation to a feature in pyhton
Python
0 vote223 views1 answer
Get or create django
Python
3 votes241 views1 answer
Last history of whatsapp message with python
Python
0 vote234 views1 answer
DataFrame.plot.line() method: | dataframe line plot
Python
1 vote235 views1 answer
Pycharm remove not in use imports
Python
128 votes233 views5 answers
Randint
Python
0 vote238 views1 answer
Find las element of array python
Python
0 vote235 views1 answer
Share x axis matplotlib
Python