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

2 votes118 views1 answer
Python merge strings in columns
Python
0 vote124 views2 answers
Django run management command from code
Python
0 vote120 views1 answer
Revesing case python
Python
0 vote117 views1 answer
Using pickle to create binary files
Python
0 vote135 views1 answer
How to make py file open in current directory
Python
36 votes129 views5 answers
Python move file
Python
7 votes170 views3 answers
Python change data type to integer
Python
1 vote130 views1 answer
Python bokeh
Python
2 votes85 views2 answers
Int' object is not subscriptable in python
Python
2 votes132 views1 answer
Colab drive access
Python