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

59 votes180 views6 answers
How to get current date in python
Python
0 vote184 views1 answer
Why python stops after plt.show()
Python
8 votes244 views1 answer
Discord.py making a bot join
Python
7 votes197 views3 answers
Python calendar
Python
0 vote208 views1 answer
Python Print Variable Using the string formatting with positional arguments {}
Python
1 vote183 views1 answer
Print every element in list python outside string
Python
0 vote181 views1 answer
How to make a config txt file on python
Python
0 vote201 views1 answer
Matplotlib bar chart from dictionary
Python
1 vote182 views2 answers
How can you know if a year is a leap year
Python
4 votes187 views5 answers
Random password generator
Python