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

2 votes113 views1 answer
Covariance matrix python
Python
0 vote122 views1 answer
From string to flaot python numpy
Python
1 vote118 views1 answer
Hashlib sha 256
Python
1 vote220 views1 answer
Flask clear session
Python Flask
25 votes128 views2 answers
How to address null in python
Python
9 votes135 views1 answer
Ardent
Python
0 vote114 views1 answer
How to make python script run forever
Python
0 vote121 views1 answer
Mudopy
Python
0 vote157 views1 answer
Use an async check function for discord.py wait_for?
Python
6 votes190 views3 answers
Extract frames from video python
Python