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 vote134 views1 answer
Aggregation with f() in django rest api
Python
7 votes135 views1 answer
Np in python
Python
2 votes128 views1 answer
Add trendline to plot matplotlib
Python
0 vote143 views1 answer
Block url selenium python
Python
1 vote140 views1 answer
Can variables have spaces python
Python
1 vote186 views1 answer
Flask form errors
Python Flask
3 votes195 views2 answers
Django timezone india
Python
43 votes157 views6 answers
Df change column names
Python
3 votes144 views4 answers
Nltk in python
Python
12 votes190 views4 answers
How to add array in python
Python