Model optimization (pruning, quantization) in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply pruning to a model layer.

Computer Vision

import tensorflow_model_optimization as tfmot
prune_low_magnitude = tfmot.sparsity.keras.[1](pruning_schedule)
pruned_model = prune_low_magnitude(model)

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

Aprune

Bprune_model

Cpruning_schedule

Dprune_low_magnitude

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect function names like 'prune' or 'prune_model'.

The function prune_low_magnitude is used to apply pruning to a model.

2fill in blank

medium

Complete the code to convert a TensorFlow model to a quantized TFLite model.

Computer Vision

converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.optimizations = [tf.lite.[1].OPTIMIZE_FOR_SIZE]
tflite_quant_model = converter.convert()

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

AOptimize

BQuantization

COptimizeMode

DOptimizeForSize

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect optimization flags like 'Quantization' or 'OptimizeForSize'.

The tf.lite.Optimize optimization flag enables quantization during TFLite conversion.

3fill in blank

hard

Fix the error in the pruning callback setup.

Computer Vision

callbacks = [tfmot.sparsity.keras.UpdatePruningStep(), tfmot.sparsity.keras.[1](log_dir)]

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

APruningSummaries

BPruningSummary

CPruningCallback

DPruningLogger

Attempts:

3 left

💡 Hint

Common Mistakes

Using singular form or incorrect callback names.

The correct callback for logging pruning summaries is PruningSummaries.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps layer names to their pruning status.

Computer Vision

pruning_status = {layer.name: layer.[1] for layer in model.layers if hasattr(layer, '[2]')}

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

Apruning_step

Bpruned

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing attribute names like 'pruning_step'.

We check if a layer has attribute 'pruned' and get its pruning status from 'pruned'.

5fill in blank

hard

Fill all three blanks to create a quantization-aware training model setup.

Computer Vision

import tensorflow_model_optimization as tfmot
quantize_model = tfmot.quantization.keras.[1](model)
quantize_model.compile(optimizer=[2], loss=[3])

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

Aquantize_model

B'adam'

C'sparse_categorical_crossentropy'

Dquantize_annotate_model

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong function names or loss strings.

The function to prepare a model for quantization-aware training is quantize_annotate_model. The optimizer is 'adam' and the loss is 'sparse_categorical_crossentropy'.

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