Model optimization for serving (quantization, pruning) in MLOps - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is quantization in model optimization?

Quantization means making the model use smaller numbers to represent data. This makes the model faster and smaller without losing much accuracy.

beginner

Explain pruning in the context of machine learning models.

Pruning removes parts of the model that are not very important. This makes the model simpler and faster to run.

intermediate

How does quantization help in serving machine learning models?

Quantization reduces the size of the model and speeds up predictions by using fewer bits for numbers, which helps when serving models on devices with limited resources.

intermediate

What is a common effect of pruning on model accuracy?

Pruning can slightly reduce accuracy if too much is removed, but careful pruning keeps accuracy high while improving speed and size.

beginner

Name two benefits of model optimization techniques like quantization and pruning.

They make models smaller and faster, which helps run them on devices with less memory and compute power.

What does quantization primarily reduce in a machine learning model?

A The number of training samples

B The number size used to store weights

C The number of layers

D The number of output classes

Quantization reduces the size of numbers used to store model weights, making the model smaller and faster.

What is the main goal of pruning a model?

A To increase training time

B To add more neurons

C To remove less important parts

D To change the model architecture completely

Pruning removes less important parts of the model to make it simpler and faster.

Which of these is a benefit of model quantization?

A Reduces memory usage

B Increases model size

C Slows down inference

D Requires more training data

Quantization reduces memory usage by using smaller number formats.

What can happen if pruning is too aggressive?

A Model accuracy may drop

B Model becomes larger

C Training time increases

D Model outputs random results

Removing too many parts can reduce the model's accuracy.

Which technique helps deploy models on devices with limited resources?

A Data augmentation

B Adding more layers

C Increasing batch size

D Pruning and quantization

Pruning and quantization reduce model size and speed up inference, helping deployment on limited devices.

Describe what quantization and pruning do to a machine learning model and why they are useful for serving.

Think about how to make a model easier to run on small devices.

Explain the trade-offs involved when applying pruning and quantization to a model.

Optimization can affect accuracy; consider the balance.

Practice

1. What is the main goal of quantization in model optimization for serving?

easy

A. Increase the size of the model for better performance

B. Reduce the precision of numbers to make the model smaller and faster

C. Add more neurons to improve accuracy

D. Remove entire layers from the model to simplify it

Solution

1. Step 1: Understand quantization purpose

   Quantization reduces the number precision (like from 32-bit to 8-bit) to save memory and speed up computation.

2. Step 2: Compare options

   Removing layers is pruning, adding neurons increases size, increasing size is opposite of optimization.

3. Final Answer:

   Reduce the precision of numbers to make the model smaller and faster -> Option B

4. Quick Check:

   Quantization = Reduce precision [OK]

Hint: Quantization means lowering number precision to save space [OK]

Common Mistakes:

• Confusing pruning with quantization
• Thinking quantization adds complexity
• Believing quantization increases model size

2. Which of the following is the correct syntax to apply pruning using TensorFlow Model Optimization API in Python?

easy

A. pruned_model = tfmot.sparsity.keras.prune_low_magnitude(model, pruning_schedule=pruning_schedule)

B. pruned_model = tf.prune_low_magnitude(model, schedule=pruning_schedule)

C. pruned_model = tfmot.prune_low_magnitude(model, pruning_schedule=pruning_schedule)

D. pruned_model = tfmot.sparsity.prune_low_magnitude(model, pruning_schedule)

Solution

1. Step 1: Recall TensorFlow pruning API structure

   The pruning function is under tfmot.sparsity.keras and requires the pruning_schedule argument.

2. Step 2: Check syntax correctness

   pruned_model = tfmot.sparsity.keras.prune_low_magnitude(model, pruning_schedule=pruning_schedule) matches the correct full path and argument names. Others miss parts or have wrong argument names.

3. Final Answer:

   pruned_model = tfmot.sparsity.keras.prune_low_magnitude(model, pruning_schedule=pruning_schedule) -> Option A

4. Quick Check:

   Correct pruning syntax = pruned_model = tfmot.sparsity.keras.prune_low_magnitude(model, pruning_schedule=pruning_schedule) [OK]

Hint: TensorFlow pruning is under tfmot.sparsity.keras with pruning_schedule [OK]

Common Mistakes:

• Omitting 'keras' in the API path
• Using wrong argument names
• Calling pruning directly from tf module

3. Given the following PyTorch code snippet for quantization, what will be the output type of the model's weights after applying dynamic quantization?

import torch
import torch.nn as nn

model = nn.Linear(10, 5)
quantized_model = torch.quantization.quantize_dynamic(model, {nn.Linear}, dtype=torch.qint8)
print(type(quantized_model.weight()))

medium

A. TypeError: 'weight' is not callable

B.

C. AttributeError: 'Linear' object has no attribute 'weight'

D.

Solution

1. Step 1: Analyze dynamic quantization effect

   torch.quantization.quantize_dynamic converts nn.Linear to torch.nn.quantized.dynamic.Linear, where weight is a method returning dequantized weights as torch.Tensor.

2. Step 2: Trace the print statement

   quantized_model.weight() succeeds, returning a torch.Tensor (fp32 dequantized), so print(type(...)) outputs <class 'torch.Tensor'>.

3. Final Answer:

   <class 'torch.Tensor'> -> Option D

4. Quick Check:

   Dynamic quant: weight() returns Tensor [OK]

Hint: Dynamic quantization makes weight() callable returning Tensor [OK]

Common Mistakes:

• Thinking weight remains non-callable attribute like original Linear
• Confusing quantized_model type with weight type
• Expecting error on quantized model weight access

4. You tried pruning a TensorFlow model but got an error: AttributeError: module 'tensorflow_model_optimization' has no attribute 'sparsity'. What is the most likely cause?

medium

A. The tensorflow_model_optimization package is not installed

B. You used the wrong pruning schedule argument

C. You forgot to import tensorflow_model_optimization as tfmot

D. Pruning is not supported in TensorFlow

Solution

1. Step 1: Understand the error message

   The error says the module has no attribute 'sparsity', which usually means the package is missing or outdated.

2. Step 2: Check common causes

   If the package is not installed, Python cannot find the 'sparsity' submodule. Importing incorrectly or wrong argument causes different errors.

3. Final Answer:

   The tensorflow_model_optimization package is not installed -> Option A

4. Quick Check:

   Missing package = AttributeError [OK]

Hint: Missing package causes AttributeError on submodules [OK]

Common Mistakes:

• Assuming import alias causes error
• Blaming pruning schedule argument
• Thinking pruning unsupported in TensorFlow

5. You want to optimize a large deep learning model for mobile deployment by combining pruning and quantization. Which sequence of steps is best to minimize model size and maintain accuracy?

hard

A. Apply quantization first, then prune the model to remove weights

B. Train the model with quantization-aware training, then prune after deployment

C. First prune the model to remove unimportant weights, then apply quantization to reduce number precision

D. Only prune the model; quantization is not compatible with pruning

Solution

1. Step 1: Understand pruning and quantization order

   Pruning removes unimportant weights first, reducing model size and complexity.

2. Step 2: Apply quantization after pruning

   Quantization then reduces number precision on the smaller pruned model, further shrinking size and speeding inference.

3. Final Answer:

   First prune the model to remove unimportant weights, then apply quantization to reduce number precision -> Option C

4. Quick Check:

   Prune first, then quantize = First prune the model to remove unimportant weights, then apply quantization to reduce number precision [OK]

Hint: Prune first to shrink, then quantize to compress numbers [OK]

Common Mistakes:

• Quantizing before pruning reduces pruning effectiveness
• Thinking pruning and quantization cannot be combined
• Pruning after deployment is too late