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 vote287 views1 answer
Python von konsoleeinlesen
Python
0 vote271 views1 answer
Get most recurring element in a list python
Python
0 vote276 views1 answer
Ipywidgets unobserve functools partial
Python
1 vote284 views1 answer
How to iterate pyspark dataframe
Python
1 vote255 views1 answer
Check if coroutine python
Python
11 votes250 views3 answers
How to do pandas profiling
Python
-1 vote258 views1 answer
Colours seaborn
Python
0 vote309 views1 answer
.comments.all order django
Python Django
1 vote266 views1 answer
ValueError: cannot mask with array containing NA / NaN values
Python
1 vote283 views1 answer
Python link to jpg
Python