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

3 votes338 views1 answer
Python wait 5 seconds then display
Python
0 vote319 views1 answer
Launching tensorboard from a python script
Python
2 votes320 views1 answer
How to set pyautogui at certain speed
Python
0 vote307 views2 answers
Correlation with target variable python
Python
-1 vote285 views1 answer
Python chunk up list
Python
0 vote326 views1 answer
Sum values
Python
0 vote337 views1 answer
Floyd triangle python
Python
4 votes295 views1 answer
Python make integer into a list
Python
0 vote307 views1 answer
Find the path of python executable
Python
1 vote327 views1 answer
Not getting spanish characters python
Python