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 vote224 views1 answer
Google translator api pyhton
Python
6 votes227 views2 answers
Jupyter display all columns
Python
0 vote220 views1 answer
Print("python is good")
Python
0 vote225 views1 answer
Abstract user in django
Python
0 vote237 views1 answer
Data format pandas
Python
0 vote220 views1 answer
Change month name in python
Python
0 vote217 views1 answer
How to deploy a file size greater than 100mb on pythonanywhere
Python
1 vote214 views1 answer
Create np nan array
Python
0 vote225 views1 answer
How to check if a variable in python is a specific data type
Python
1 vote279 views1 answer
On member leave event in discord.py
Python