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

1 vote167 views1 answer
Python sum of list axes
Python
0 vote152 views1 answer
Hebrew range
Python
43 votes208 views6 answers
Python requests get
Python
0 vote257 views1 answer
Can u length a dictionary in python
Python
12 votes181 views6 answers
Set python 3 as default mac
Python
0 vote165 views2 answers
Arma-garch python
Python
0 vote200 views1 answer
How to iterate through a list of numbers in python
Python
0 vote175 views1 answer
Matplotlib overlapping labels
Python
8 votes231 views1 answer
Python loop certain number of times
Python
0 vote172 views2 answers
Python stop while loop after time
Python