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

2 votes367 views1 answer
Remove a file or dir in linux or mac or ubuntu
Python
0 vote381 views1 answer
Create jwt token in django
Python Django
0 vote316 views9 answers
Odoo.py odoo 14
Python
18 votes339 views3 answers
Dataframe check for nan in iterrows
Python
67 votes351 views4 answers
How to know the version of python using cmd
Python
0 vote413 views1 answer
Find the closest smaller value in an array python
Python
5 votes345 views2 answers
Remove all of same value python list
Python
4 votes329 views5 answers
Random password generator
Python
0 vote363 views1 answer
Created by and updated by in django
Python
1 vote339 views1 answer
How to set environment variable in pycharm
Python