Model optimization (pruning, quantization) in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding Model Pruning Effects

What is the primary effect of pruning a convolutional neural network model?

A It increases the model size by adding redundant neurons to improve accuracy.

B It converts the model weights from floating-point to integer format to save memory.

C It reduces the number of parameters by removing less important weights, which can speed up inference.

D It changes the model architecture by adding more convolutional layers.

💡 Hint

Think about how pruning affects model size and speed.

Pruning removes less important weights, reducing model size and speeding up inference without changing the architecture.

❓ Predict Output

intermediate

Output of Quantization on Model Weights

Given a floating-point weight tensor [0.9, -1.2, 0.3, 2.7], what is the output after 8-bit symmetric quantization with scale 0.1 and zero-point 0?

Computer Vision

import numpy as np
weights = np.array([0.9, -1.2, 0.3, 2.7])
scale = 0.1
zero_point = 0
quantized = np.round(weights / scale) + zero_point
quantized = quantized.astype(np.int8)
print(quantized.tolist())

A [90, -120, 30, 270]

B [9, -12, 3, 27]

C [8, -11, 2, 26]

D [10, -13, 4, 28]

💡 Hint

Divide each weight by the scale and round to nearest integer.

Each weight is divided by 0.1 and rounded: 0.9/0.1=9, -1.2/0.1=-12, etc.

❓ Hyperparameter

advanced

Choosing Pruning Percentage

You want to prune a deep CNN model to reduce size but keep accuracy loss under 2%. Which pruning percentage is most reasonable to start with?

A Prune 0% weights since pruning always reduces accuracy.

B Prune 50% of weights to balance size and accuracy.

C Prune 90% of weights to maximize compression.

D Prune 10% of weights to keep accuracy mostly intact.

💡 Hint

Start with a small pruning amount to avoid big accuracy drops.

Pruning 10% is a safe start to reduce size with minimal accuracy loss; pruning 90% is too aggressive and likely harms accuracy.

❓ Metrics

advanced

Evaluating Quantized Model Accuracy

After quantizing a model, you observe the accuracy dropped from 92% to 89%. What metric best describes this change?

A Absolute accuracy drop of 3 percentage points.

B Relative accuracy increase of 3%.

C Accuracy remains unchanged.

D Accuracy improved by 3 percentage points.

💡 Hint

Calculate the difference between original and quantized accuracy.

The accuracy dropped by 3 points (92% - 89% = 3%).

🔧 Debug

expert

Debugging Pruning Code Causing Runtime Error

Consider this pruning code snippet for a PyTorch model:

for name, param in model.named_parameters():
    if 'weight' in name:
        mask = (param.abs() > threshold)
        param.data = param.data * mask

What is the cause of the runtime error?

A The threshold variable is not defined before use.

B The condition 'weight' in name is incorrect and never true.

C The loop modifies param.data in-place which is not allowed in PyTorch.

D The mask is a boolean tensor and multiplying it with param.data causes a type mismatch error.

💡 Hint

Look for undefined variables in the code.

The threshold variable is not defined before use, causing a NameError.

Practice

1. What is the main goal of model pruning in computer vision?

easy

A. To remove less important parts of the model to reduce size

B. To increase the number of layers in the model

C. To add more training data for better accuracy

D. To convert the model to a different programming language

Solution

1. Step 1: Understand pruning concept

   Pruning means removing parts of the model that contribute less to its output.

2. Step 2: Identify pruning goal

   The goal is to reduce model size and speed up inference by cutting unnecessary parts.

3. Final Answer:

   To remove less important parts of the model to reduce size -> Option A

4. Quick Check:

   Pruning = Remove less important parts [OK]

Hint: Pruning cuts unneeded parts to shrink model size [OK]

Common Mistakes:

• Thinking pruning adds layers instead of removing
• Confusing pruning with data augmentation
• Believing pruning changes programming language

2. Which of the following is the correct way to apply quantization in TensorFlow Lite?

easy

A. model = tf.lite.TFLiteConverter.from_keras_model(model).convert()

B. converter.optimizations = [tf.lite.Optimize.DEFAULT]

C. model.compile(optimizer='adam', loss='mse')

D. model.fit(x_train, y_train, epochs=10)

Solution

1. Step 1: Identify quantization syntax

   In TensorFlow Lite, quantization is enabled by setting converter.optimizations to Optimize.DEFAULT.

2. Step 2: Check other options

   model = tf.lite.TFLiteConverter.from_keras_model(model).convert() converts model but does not enable quantization. Options B and C are training commands, not quantization.

3. Final Answer:

   converter.optimizations = [tf.lite.Optimize.DEFAULT] -> Option B

4. Quick Check:

   Quantization flag = converter.optimizations [OK]

Hint: Quantization needs converter.optimizations set to Optimize.DEFAULT [OK]

Common Mistakes:

• Confusing model conversion with quantization
• Using training commands instead of conversion flags
• Missing the optimization setting for quantization

3. Given this PyTorch pruning code snippet, what will be the output size of the model's first linear layer weights after pruning 20% of connections?

import torch
import torch.nn.utils.prune as prune

model = torch.nn.Sequential(
    torch.nn.Linear(100, 50),
    torch.nn.ReLU()
)
prune.l1_unstructured(model[0], name='weight', amount=0.2)
pruned_weights = model[0].weight
print((pruned_weights != 0).sum().item())

medium

A. 8000

B. 5000

C. 10000

D. 4000

Solution

1. Step 1: Calculate total weights

   The first linear layer has 100 inputs and 50 outputs, so total weights = 100 * 50 = 5000.

2. Step 2: Calculate remaining weights after pruning

   Pruning 20% removes 20% of weights, so remaining weights = 80% of 5000 = 4000.

3. Step 3: Understand pruning method

   PyTorch's l1_unstructured pruning does not remove weights but masks them, so the weight tensor size remains 5000, but the number of non-zero weights is 4000.

4. Step 4: Check print output

   The print statement counts non-zero weights, so output is 4000.

5. Final Answer:

   4000 -> Option D

6. Quick Check:

   5000 * 0.8 = 4000 [OK]

Hint: Remaining weights = total * (1 - pruning amount) [OK]

Common Mistakes:

• Calculating total weights incorrectly
• Using pruning amount as remaining instead of removed
• Confusing layer input/output dimensions

4. You tried to quantize a model but got an error: AttributeError: 'TFLiteConverter' object has no attribute 'optimizations'. What is the likely cause?

medium

A. Quantization requires training the model again

B. Model is too large to quantize

C. Using an outdated TensorFlow version without quantization support

D. The model has no weights to quantize

Solution

1. Step 1: Understand the error

   The error says the converter object lacks 'optimizations' attribute, meaning the TensorFlow version is old.

2. Step 2: Identify cause

   Older TensorFlow versions do not support the 'optimizations' attribute needed for quantization.

3. Final Answer:

   Using an outdated TensorFlow version without quantization support -> Option C

4. Quick Check:

   Missing attribute = outdated TensorFlow [OK]

Hint: Check TensorFlow version supports quantization features [OK]

Common Mistakes:

• Assuming model size causes attribute error
• Thinking quantization needs retraining always
• Believing model without weights causes this error

5. You want to deploy a computer vision model on a mobile device with limited memory and CPU. Which combination of optimization techniques is best to reduce model size and speed up inference without much accuracy loss?

hard

A. Apply pruning to remove unimportant weights, then quantize weights to 8-bit integers

B. Only increase model layers to improve accuracy

C. Use full precision weights and no pruning for best accuracy

D. Train longer without any model size changes

Solution

1. Step 1: Understand device constraints

   Mobile devices have limited memory and CPU, so model size and speed matter.

2. Step 2: Choose optimization techniques

   Pruning removes unnecessary weights reducing size; quantization reduces number precision speeding inference.

3. Step 3: Combine pruning and quantization

   Using both together reduces size and speeds up model with minimal accuracy loss.

4. Final Answer:

   Apply pruning to remove unimportant weights, then quantize weights to 8-bit integers -> Option A

5. Quick Check:

   Pruning + quantization = smaller, faster model [OK]

Hint: Combine pruning and quantization for efficient mobile models [OK]

Common Mistakes:

• Only increasing layers without optimization
• Ignoring quantization benefits
• Assuming full precision is always best for deployment