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

16 votes265 views6 answers
Turtle
Python
1 vote263 views1 answer
Python how to check if a functions been called
Python
1 vote233 views1 answer
How to remove seconds from datetime in python
Python
1 vote277 views4 answers
Seaborn rotate x labels
Python
4 votes271 views3 answers
How to change text in a canvas tkinter
Python
3 votes278 views2 answers
Find location of max value in python list
Python
10 votes263 views2 answers
Python - subset specific columns name in a dataframe
Python
1 vote262 views1 answer
How to install panda3d
Python
0 vote277 views1 answer
Create a file in a specific directory
Python
0 vote251 views1 answer
How to call column name with space in python
Python