Model parameters inspection in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What are model parameters in PyTorch?

Model parameters are the weights and biases that the model learns during training to make predictions.

beginner

How can you access the parameters of a PyTorch model?

You can access parameters using the model.parameters() method, which returns an iterator over all parameters.

intermediate

What does named_parameters() provide compared to parameters()?

named_parameters() returns both the name and the parameter tensor, helping identify which layer the parameter belongs to.

intermediate

Why is inspecting model parameters useful?

Inspecting parameters helps understand model size, debug training issues, and verify if parameters are updating correctly.

beginner

How do you check the shape of a model parameter tensor in PyTorch?

You can check the shape by accessing the .shape attribute of the parameter tensor, e.g., param.shape.

Which PyTorch method returns an iterator over all model parameters?

A model.named_parameters()

B model.state_dict()

C model.parameters()

D model.forward()

model.parameters() returns all parameters without names.

What does named_parameters() return in PyTorch?

A Parameter names and tensors

B Only parameter tensors

C Model architecture

D Training loss values

named_parameters() returns tuples of (name, parameter tensor).

Why might you want to inspect model parameters during training?

A To load data

B To change the learning rate

C To save the model

D To check if parameters are updating

Inspecting parameters helps verify if training is working by checking updates.

How do you find the shape of a parameter tensor in PyTorch?

A param.shape

B param.length()

C param.size()

D param.dimensions()

param.shape gives the dimensions of the tensor.

Which of these is NOT a model parameter in PyTorch?

A Biases

B Input data

C Weights

D Learned tensors

Input data is not a model parameter; parameters are learned during training.

Explain how to inspect and interpret the parameters of a PyTorch model.

Think about how you would check what your model is learning.

Why is it important to look at model parameters during training?

Consider what could go wrong if parameters don't update.

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