Model parameters inspection in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to print the names of all parameters in a PyTorch model.

PyTorch

for name, param in model.[1]():
    print(name)

Drag options to blanks, or click blank then click option'

Anamed_parameters

Bparameters

Cstate_dict

Dchildren

Attempts:

3 left

💡 Hint

Common Mistakes

Using parameters() which returns only parameter values without names.

Using state_dict() which returns a dictionary, not an iterator.

The named_parameters() method returns both the parameter names and their values, which allows us to print the names.

2fill in blank

medium

Complete the code to count how many parameters in the model require gradients.

PyTorch

count = sum(p.requires_grad for p in model.[1]())
print(count)

Drag options to blanks, or click blank then click option'

Anamed_parameters

Bparameters

Cchildren

Dmodules

Attempts:

3 left

💡 Hint

Common Mistakes

Using named_parameters() when only parameters are needed.

Using children() which returns submodules, not parameters.

The parameters() method returns all parameters, and we check their requires_grad attribute to count those that require gradients.

3fill in blank

hard

Fix the error in the code to print the shape of each parameter tensor.

PyTorch

for name, param in model.named_parameters():
    print(name, param.[1])

Drag options to blanks, or click blank then click option'

Ashape

Bdim

Csize

Dlength

Attempts:

3 left

💡 Hint

Common Mistakes

Using size without parentheses, which prints the method object instead of the shape.

Using dim which returns the number of dimensions, not the shape.

Using length which is not a tensor property.

In PyTorch, shape is a property/attribute that returns the shape of a tensor as a torch.Size tuple. size is a method that requires parentheses (size()); without them, it refers to the method object itself.

4fill in blank

hard

Fill the blank to create a dictionary of parameter names and their flattened sizes.

PyTorch

param_sizes = {name: param.[1]() for name, param in model.named_parameters()}

Drag options to blanks, or click blank then click option'

Asize

Bdim

Cshape

Dnumel

Attempts:

3 left

💡 Hint

Common Mistakes

Using size() or shape which return the shape tuple, not the flattened count.

Using dim which returns number of dimensions, not size.

numel() returns the total number of elements (flattened size) in the tensor.

5fill in blank

hard

Fill all three blanks to filter parameters that require gradients and create a dictionary of their names and shapes.

PyTorch

grad_params = {name: param.[1]() for name, param in model.named_parameters() if param.[2] and param.[3]

Drag options to blanks, or click blank then click option'

Asize

Brequires_grad

Cis_leaf

Dgrad

Attempts:

3 left

💡 Hint

Common Mistakes

Using grad which is None before backward pass.

Not filtering by is_leaf which may include intermediate tensors.

We get the shape with size(). We filter parameters that require gradients (requires_grad) and are leaf tensors (is_leaf) to ensure they are trainable parameters.

Practice

1. What does the named_parameters() method in a PyTorch model return?

easy

A. The optimizer's learning rate

B. An iterator over tuples of parameter names and their tensors

C. The model's training loss values

D. A list of all model layers

Solution

1. Step 1: Understand the purpose of named_parameters()

   This method is designed to give access to each parameter's name and its tensor, which includes weights and biases.

2. Step 2: Identify what it returns

   It returns an iterator over tuples, where each tuple contains the parameter's name and the tensor itself.

3. Final Answer:

   An iterator over tuples of parameter names and their tensors -> Option B

4. Quick Check:

   named_parameters() = iterator of (name, tensor) [OK]

Hint: Remember: named_parameters() lists names and tensors [OK]

Common Mistakes:

• Confusing parameters with layers
• Thinking it returns loss or optimizer info
• Assuming it returns just tensors without names

2. Which of the following code snippets correctly prints the names and shapes of all parameters in a PyTorch model model?

easy

A. for name, param in model.named_parameters(): print(name, param.shape)

B. for param in model.parameters(): print(param.name, param.shape)

C. print(model.parameters().names())

D. model.print_parameters()

Solution

1. Step 1: Check correct method usage

   The method named_parameters() returns (name, parameter) pairs, so unpacking into two variables is correct.

2. Step 2: Verify printing name and shape

   Accessing param.shape gives the tensor shape. for name, param in model.named_parameters(): print(name, param.shape) correctly prints both.

3. Final Answer:

   for name, param in model.named_parameters(): print(name, param.shape) -> Option A

4. Quick Check:

   Use named_parameters() with unpacking [OK]

Hint: Use named_parameters() to get names and tensors [OK]

Common Mistakes:

• Trying to access .name on param tensor (no such attribute)
• Using parameters() without names
• Calling non-existent methods like print_parameters()

3. Given the following PyTorch model code, what will be the output of the print statement?

import torch.nn as nn

class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 3)
        self.fc2 = nn.Linear(3, 2)

model = SimpleNet()
params = list(model.named_parameters())
print(len(params))

medium

A. 2

B. 6

C. 4

D. 3

Solution

1. Step 1: Count parameters in each layer

   Each nn.Linear has weights and biases, so 2 parameters per layer.

2. Step 2: Calculate total parameters

   Two layers x 2 parameters each = 4 parameters total.

3. Final Answer:

   4 -> Option C

4. Quick Check:

   2 layers x 2 params = 4 [OK]

Hint: Each Linear layer has weight and bias parameters [OK]

Common Mistakes:

• Counting only layers, not parameters
• Assuming one parameter per layer
• Confusing number of parameters with tensor sizes

4. You wrote this code to print model parameter names and shapes but get an error:

for name, param in model.parameters():
    print(name, param.shape)

What is the error and how to fix it?

medium

A. The loop syntax is wrong; use for param, name in model.parameters()

B. param.shape is invalid; use param.size() instead

C. You must call model.parameters().items() to get name and param

D. model.parameters() returns tensors only; use model.named_parameters() to get names

Solution

1. Step 1: Understand what model.parameters() returns

   This method returns only parameter tensors, no names.

2. Step 2: Correct method to get names and parameters

   Use model.named_parameters() which returns (name, param) pairs.

3. Final Answer:

   model.parameters() returns tensors only; use model.named_parameters() to get names -> Option D

4. Quick Check:

   parameters() = tensors only, named_parameters() = (name, tensor) [OK]

Hint: Use named_parameters() to get names with tensors [OK]

Common Mistakes:

• Trying to unpack parameters() into name and param
• Using .items() on parameters() which is not a dict
• Swapping variable order in for loop

5. You want to calculate the total number of trainable parameters in a PyTorch model model. Which code snippet correctly computes this?

hard

A. sum(p.numel() for p in model.parameters() if p.requires_grad)

B. len(model.named_parameters())

C. sum(p.shape for p in model.parameters())

D. model.count_parameters()

Solution

1. Step 1: Understand what counts as trainable parameters

   Only parameters with requires_grad=True are trainable.

2. Step 2: Use numel() to count elements in each tensor

   Summing p.numel() for all trainable parameters gives total count.

3. Final Answer:

   sum(p.numel() for p in model.parameters() if p.requires_grad) -> Option A

4. Quick Check:

   Sum numel() of trainable params = total count [OK]

Hint: Sum numel() of parameters with requires_grad True [OK]

Common Mistakes:

• Using len() which counts parameters, not elements
• Trying to sum shapes directly (shapes are tuples)
• Assuming model has count_parameters() method