__init__ for layers in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the purpose of the __init__ method in a PyTorch layer class?

The __init__ method sets up the layer by defining its parameters and sub-layers. It prepares the layer to be used later in the forward pass.

beginner

Why do we call super().__init__() inside the __init__ method of a PyTorch layer?

Calling super().__init__() initializes the parent class nn.Module, which is necessary for PyTorch to track parameters and manage the layer properly.

beginner

How do you define a fully connected layer inside the __init__ method?

You create an instance of nn.Linear with input and output sizes, for example: self.fc = nn.Linear(input_size, output_size).

intermediate

What happens if you forget to call super().__init__() in your layer's __init__?

PyTorch will not properly register the layer's parameters, which can cause errors during training or the model not learning correctly.

beginner

Can you store multiple layers inside the __init__ method? How?

Yes, you can define multiple layers as attributes, for example: self.conv1 = nn.Conv2d(...) and self.fc1 = nn.Linear(...). This organizes the model parts clearly.

What is the first thing you should do inside the __init__ method of a PyTorch layer?

A Call <code>super().__init__()</code>

B Define the forward method

C Initialize the optimizer

D Load the dataset

Calling super().__init__() initializes the base nn.Module class, which is essential for the layer to work properly.

How do you define a linear layer with 10 inputs and 5 outputs inside __init__?

A self.fc = nn.Linear(5, 10)

B self.fc = nn.Linear(10, 5)

C self.fc = nn.Conv2d(10, 5)

D self.fc = nn.Linear()

The first argument is input size (10), the second is output size (5) for nn.Linear.

What happens if you do not call super().__init__() in your layer?

A Parameters are not registered properly

B The model trains faster

C The forward method runs twice

D Nothing happens

Without calling super().__init__(), PyTorch cannot track parameters, causing training issues.

Where do you define the layers like convolution or linear in a PyTorch model?

A Outside the class

B Inside the <code>forward</code> method

C Inside the <code>__init__</code> method

D In the training loop

Layers are defined in __init__ so they are created once and reused during forward passes.

Can you define multiple layers inside __init__?

A Only if you use a list

B No, only one layer per class

C Only if they are the same type

D Yes, by assigning them as attributes

You can define many layers as attributes like self.conv1, self.fc1, etc.

Explain the role of the __init__ method when creating a custom PyTorch layer.

Think about what happens before the model processes data.

Describe what could go wrong if you forget to call super().__init__() in your PyTorch layer's __init__.

Consider how PyTorch manages model parts internally.

Practice

1. What is the main purpose of the __init__ method in a PyTorch layer class?

easy

A. To save the model to disk

B. To set up the parts of the layer like linear or dropout layers

C. To train the model on data

D. To run the forward pass of the model

Solution

1. Step 1: Understand the role of __init__ in PyTorch

   The __init__ method is used to prepare the layer by defining its parts, such as linear or dropout layers.

2. Step 2: Differentiate from other methods

   The forward pass runs the data through the layer, training updates weights, and saving stores the model. These are not done in __init__.

3. Final Answer:

   To set up the parts of the layer like linear or dropout layers -> Option B

4. Quick Check:

   __init__ prepares layer parts = D [OK]

Hint: Remember: __init__ builds the layer parts first [OK]

Common Mistakes:

• Confusing __init__ with the forward method
• Thinking __init__ trains the model
• Assuming __init__ saves the model

2. Which of the following is the correct way to start the __init__ method in a PyTorch layer class?

easy

A. def __init__(self): super()

B. def __init__(): super().__init__()

C. def __init__(self): super().__init__()

D. def __init__(self): init.super()

Solution

1. Step 1: Check the method signature

   The __init__ method must have self as the first parameter.

2. Step 2: Call the parent class initializer correctly

   Use super().__init__() to properly initialize the parent class.

3. Final Answer:

   def __init__(self): super().__init__() -> Option C

4. Quick Check:

   Correct __init__ start = B [OK]

Hint: Always include self and call super().__init__() first [OK]

Common Mistakes:

• Omitting self parameter
• Calling super() without __init__()
• Wrong method signature without self

3. What will be the output shape of the linear layer defined below inside __init__ when input tensor has shape (10, 5)?

class MyLayer(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = torch.nn.Linear(5, 3)

    def forward(self, x):
        return self.linear(x)

layer = MyLayer()
input_tensor = torch.randn(10, 5)
output = layer(input_tensor)
print(output.shape)

medium

A. torch.Size([10, 3])

B. torch.Size([5, 3])

C. torch.Size([10, 5])

D. torch.Size([3, 10])

Solution

1. Step 1: Understand the linear layer dimensions

   The linear layer is defined as Linear(5, 3), so it expects input features of size 5 and outputs size 3.

2. Step 2: Match input tensor shape and output shape

   The input tensor has shape (10, 5), meaning 10 samples with 5 features each. The output will have shape (10, 3) after the linear layer.

3. Final Answer:

   torch.Size([10, 3]) -> Option A

4. Quick Check:

   Input features 5 to output 3, batch 10 = torch.Size([10, 3]) [OK]

Hint: Output shape = (batch size, output features) [OK]

Common Mistakes:

• Confusing input and output feature sizes
• Mixing batch size with feature dimension
• Ignoring the linear layer's output size

4. Identify the error in the following __init__ method of a PyTorch layer:

class MyLayer(torch.nn.Module):
    def __init__(self):
        self.linear = torch.nn.Linear(4, 2)
        super().__init__()

medium

A. Missing return statement in __init__

B. self.linear should be defined outside __init__

C. No error, code is correct

D. super().__init__() must be called before defining layers

Solution

1. Step 1: Check order of super().__init__() call

   In PyTorch, super().__init__() must be called first inside __init__ to properly initialize the parent class.

2. Step 2: Identify the error in the code

   The code calls super().__init__() after defining self.linear, which is incorrect and can cause errors.

3. Final Answer:

   super().__init__() must be called before defining layers -> Option D

4. Quick Check:

   Call super().__init__() first in __init__ = C [OK]

Hint: Always call super().__init__() before defining layers [OK]

Common Mistakes:

• Defining layers before calling super().__init__()
• Thinking __init__ needs a return statement
• Defining layers outside __init__

5. You want to create a custom PyTorch layer that has two linear layers and a dropout layer. Which __init__ method correctly sets up these parts?

hard

A. def __init__(self):
super().__init__()
self.linear1 = torch.nn.Linear(10, 20)
self.linear2 = torch.nn.Linear(20, 5)
self.dropout = torch.nn.Dropout(0.3)

B. def __init__(self):
self.linear1 = torch.nn.Linear(10, 20)
self.linear2 = torch.nn.Linear(20, 5)
self.dropout = torch.nn.Dropout(0.3)
super().__init__()

C. def __init__(self):
super().__init__()
self.linear1 = torch.nn.Linear(20, 10)
self.linear2 = torch.nn.Linear(5, 20)
self.dropout = torch.nn.Dropout(0.3)

D. def __init__(self):
super().__init__()
self.linear1 = torch.nn.Linear(10, 20)
self.linear2 = torch.nn.Linear(5, 20)
self.dropout = torch.nn.Dropout(0.3)

Solution

1. Step 1: Check the order of super().__init__() call

   It must be called first to initialize the parent class properly.

2. Step 2: Verify layer dimensions and definitions

   Linear layers should connect properly: first from 10 to 20, second from 20 to 5. Dropout is correctly defined with 0.3 probability.

3. Step 3: Identify the correct option

   def __init__(self): super().__init__() self.linear1 = torch.nn.Linear(10, 20) self.linear2 = torch.nn.Linear(20, 5) self.dropout = torch.nn.Dropout(0.3) matches correct order, layer sizes, and dropout setup. Codes that call super().__init__() last or have mismatched dimensions like Linear(20,10) and Linear(5,20) are incorrect.

4. Final Answer:

   def __init__(self): super().__init__() self.linear1 = torch.nn.Linear(10, 20) self.linear2 = torch.nn.Linear(20, 5) self.dropout = torch.nn.Dropout(0.3) -> Option A

5. Quick Check:

   Correct order and layer sizes = A [OK]

Hint: Call super first, then define layers with matching sizes [OK]

Common Mistakes:

• Calling super().__init__() last
• Using wrong input/output sizes for linear layers
• Misplacing dropout layer definition