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

20 votes115 views2 answers
Python list of paths
Python
2 votes131 views1 answer
Django queryset get all distinct
Python Django
0 vote108 views1 answer
Python print top 5 results of array
Python
0 vote107 views1 answer
How to use cv2.COLOR_BGR2GRAY
Python
1 vote117 views1 answer
Print(int())
Python
0 vote116 views1 answer
How to limit a command to a role in discord.py
Python
7 votes120 views1 answer
Python marker size
Python
0 vote135 views1 answer
Is python3 enough for react native
Python
0 vote125 views1 answer
Creation 2eme fenetre tkinter
Python
2 votes110 views1 answer
Python half of string
Python