AttributeError: 'super' object has no attribute '_LinearRegressionModel__init'

[MaryamSaremiKermanshahi]

Hey, I am trying 01_pytorch_workflow on my colab,
when I want to check my LinearRegressionModel, with rhis code:

from torch import nn
#Creating linear regression model
class LinearRegressionModel(nn.Module): #almost everything in PyTorch inherits from nn.Module
def init(self):
super().__init()

#initiallizing model parameters
self.weight = nn.Parameter(torch.randn(1,
                                      requires_grad=True,
                                      dtype=torch.float))

self.bias = nn.Parameter(torch.randn(1,
                                    require_grad=True,
                                    dtype=torch.float))
#Forward method to define the computation in the model
def forward(self, x: torch.Tensor) -> torch.Tensor: #<- "x" is the input data
  return self.weights * x + self.bias #this is the linear regression formula

#Create a random seed
torch.manual_seed(42)

#Create an instance of the model (this is a subclass of nn.Module)
model_0 = LinearRegressionModel()

model_0

I face to this error:
AttributeError: 'super' object has no attribute '_LinearRegressionModel__init'

"Would you please help me, get rid of the error"

[LuluW8071]

@MaryamSaremiKermanshahi I think you didnt put double underscore on right side of super(),__init__ causing AttributeError: 'super' object has no attribute

Here's the corrected version:

# Create a linear regression model class
class LinearRegressionModel(nn.Module):         # nn.Module contains building blocks(subclass) of neural networks
  def __init__(self):
    super().__init__()
    self.weights = nn.Parameter(torch.randn(1,
                                           requires_grad = True,   # set parameter to be updated via gradient descent -> True
                                           dtype = torch.float))
    self.bias = nn.Parameter(torch.randn(1,
                                         requires_grad = True,     # set parameter to be updated via gradient descent -> True
                                         dtype = torch.float)) 

  # Forward method to define the computation in model
  def forward(self, x:torch.Tensor) -> torch.Tensor:    # 'x' is input data
    return self.weights * x + self.bias   # Linear regression formula

[MaryamSaremiKermanshahi]

Thank you