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

5 votes168 views1 answer
Append item to array python
Python
0 vote175 views1 answer
Find the highest id in model django
Python
0 vote178 views3 answers
Py draw matrix of black square and white circle
Python
2 votes161 views1 answer
Numpy how to slice individual columns
Python
0 vote172 views1 answer
Docstrinfs pyt
Python
0 vote165 views2 answers
Sumx and ABS in power bi
Python
3 votes216 views1 answer
Remove keys from dict python
Python
1 vote146 views2 answers
SSL: CERTIFICATE_VERIFY_FAILED mongo atlas
Python
0 vote187 views1 answer
How to find empty rows of a dataset in python
Python
0 vote162 views2 answers
Conda install dash
Python