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 vote297 views2 answers
Python check if input contains letters
Python
0 vote274 views2 answers
Pywhatkit.text to handwriting(text,rgb=[0,0,0])
Python
61 votes307 views6 answers
Python sort dict by key
Python
0 vote266 views1 answer
Import re #your code goes here number=input() pattern=r"(1|8|9)[0-9]+" match=re.match(pattern,number) of lane(number)==8: if(match): print("value") else: print("invalid") else print("invalid")
Python
2 votes272 views1 answer
How to return total elements in database django
Python
0 vote283 views1 answer
How to use startswith() with list
Python
0 vote298 views1 answer
Pydub audiosegment to numpy array
Python
26 votes313 views6 answers
Python turtle
Python
1 vote296 views1 answer
Matplotlib show imaginary numbers
Python
58 votes364 views6 answers
Python class
Python