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.