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 vote213 views2 answers
Python - create frequency table between two columns
Python
5 votes210 views1 answer
Python read file without newline
Python
5 votes199 views5 answers
How to take space separated input in python
Python
7 votes149 views1 answer
Dataframe count null values
Python
15 votes186 views4 answers
How to find last element in array python
Python
8 votes207 views3 answers
Print traceback python
Python
6 votes148 views1 answer
Business logic in django
Python
2 votes240 views1 answer
Pygame get screen width and height
Python
0 vote196 views1 answer
Check strict superset hackerrank solution
Python
9 votes207 views2 answers
Pygame play sound
Python