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 vote129 views1 answer
Spacy matcher syntax
Python
0 vote220 views1 answer
How do you read from a dictionary in python
Python
8 votes166 views3 answers
Jinja templates tables
Python
1 vote182 views5 answers
Filter function in python
Python
10 votes141 views1 answer
Pandas sample seed
Python
0 vote194 views1 answer
Python float to string n decimals
Python
0 vote125 views2 answers
How to make a discord moderation bot python
Python
0 vote145 views1 answer
Python crear variables
Python
0 vote175 views1 answer
Stickler Thief or Maximum sum such that no two elements are adjacent
Python
22 votes125 views1 answer
Python isset key
Python