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 vote148 views1 answer
Computecost pyspark
Python
1 vote158 views1 answer
X= [10] def List_ex(): x.append(20) def add_list(): x=[30,40] x.append(50) print (x) List_ex() print (x) add_list() print (x)
Python
0 vote196 views1 answer
Delete history django simple
Python Django
0 vote180 views1 answer
Treat NaN as a category
Python
0 vote175 views1 answer
Using built-in crawlers is very simple. A minimal example is shown as follows.
Python
0 vote148 views1 answer
Python set workspace dir
Python
1 vote193 views2 answers
Tensor get value
Python
0 vote285 views1 answer
Django show image in admin page
Python Django
0 vote156 views1 answer
Withdraw() opposite tjinter
Python
134 votes130 views15 answers
Ternary operator python
Python