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 vote252 views1 answer
Additon of multiple duration timestamps python
Python
0 vote221 views1 answer
Python read binary
Python
1 vote248 views1 answer
Python delete text in text file
Python
0 vote236 views1 answer
Chromebook install pip
Python
1 vote233 views1 answer
From time import sleep, time
Python
2 votes237 views1 answer
How to resize tkinter window
Python
0 vote269 views1 answer
Flask return 404
Python Flask
0 vote227 views1 answer
How to use a function to find the total in spyder python
Python
-1 vote237 views1 answer
Python launch prompt
Python
5 votes273 views2 answers
Python captcha
Python