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

1 vote208 views1 answer
Python MongoEngine doc
Python
0 vote204 views1 answer
Python dataset createdimension unlimited
Python
7 votes161 views3 answers
Build a discord bot to delete messages python
Python
0 vote219 views4 answers
Pandas replace word begins with contains
Python
0 vote215 views1 answer
Change a color on touch roblox
Python
2 votes276 views3 answers
How to unlist a list in python
Python
0 vote229 views1 answer
Picture as background of seaborn plot python
Python
4 votes225 views1 answer
Pandas dataframe replace inf
Python
0 vote259 views1 answer
Series object has no attribute columns
Python
21 votes212 views5 answers
Base64 python decode
Python