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 vote141 views1 answer
Html to json python
Python
5 votes172 views1 answer
Finding the index of an element in a pandas df
Python
1 vote145 views2 answers
Split a string with 2 char each in python
Python
0 vote123 views1 answer
Login_required
Python
91 votes146 views6 answers
Conda create environment python 3
Python
0 vote110 views1 answer
Width and precision thousand separetor python
Python
1 vote151 views1 answer
Python match statement
Python
1 vote147 views1 answer
Control tello drone with python
Python
27 votes150 views2 answers
What value do we get from NULL database python
Python
92 votes147 views6 answers
Turn python script into exe
Python