Model optimization for serving (quantization, pruning) in MLOps - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply post-training quantization using TensorFlow Lite.

MLOps

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
converter.optimizations = [[1]]
tflite_model = converter.convert()

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

Atf.lite.Optimize.DEFAULT

Btf.lite.Quantize.DEFAULT

Ctf.lite.Optimize.QUANTIZE

Dtf.lite.Optimize.NONE

Attempts:

3 left

💡 Hint

Common Mistakes

Using a non-existent flag like tf.lite.Quantize.DEFAULT

Using NONE disables optimization, so no quantization happens

The correct optimization flag for post-training quantization in TensorFlow Lite is tf.lite.Optimize.DEFAULT. This enables default optimizations including quantization.

2fill in blank

medium

Complete the code to prune a Keras model with 50% sparsity.

MLOps

import tensorflow_model_optimization as tfmot
prune_low_magnitude = tfmot.sparsity.keras.prune_low_magnitude
pruning_params = {'pruning_schedule': tfmot.sparsity.keras.PolynomialDecay(initial_sparsity=0.0, final_sparsity=[1], begin_step=0, end_step=1000)}
model = prune_low_magnitude(original_model, **pruning_params)

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

A50

B0.5

C0.05

D5

Attempts:

3 left

💡 Hint

Common Mistakes

Using 50 instead of 0.5 causes errors because sparsity must be between 0 and 1

Using 5 or 0.05 are incorrect values for 50% sparsity

Sparsity is expressed as a fraction between 0 and 1. For 50% sparsity, use 0.5.

3fill in blank

hard

Fix the error in the pruning callback setup to correctly update pruning steps during training.

MLOps

callbacks = [tfmot.sparsity.keras.UpdatePruningStep(), [1]]
model.fit(train_data, epochs=10, callbacks=callbacks)

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

Atf.keras.callbacks.EarlyStopping()

Btfmot.sparsity.keras.PruningCallback()

Ctfmot.sparsity.keras.PruningSummaries(log_dir)

Dtf.keras.callbacks.ModelCheckpoint()

Attempts:

3 left

💡 Hint

Common Mistakes

Using unrelated callbacks like EarlyStopping or ModelCheckpoint

Using a non-existent PruningCallback

The correct callback to add alongside UpdatePruningStep() is PruningSummaries to log pruning summaries during training.

4fill in blank

hard

Fill both blanks to create a TensorFlow Lite converter that applies quantization and sets the supported ops.

MLOps

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
converter.optimizations = [[1]]
converter.target_spec.supported_ops = [[2]]
tflite_model = converter.convert()

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

Atf.lite.Optimize.DEFAULT

Btf.lite.OpsSet.TFLITE_BUILTINS_INT8

Ctf.lite.OpsSet.TFLITE_BUILTINS

Dtf.lite.Optimize.NONE

Attempts:

3 left

💡 Hint

Common Mistakes

Using NONE disables optimization.

Using TFLITE_BUILTINS without INT8 does not fully enable quantized ops.

Use tf.lite.Optimize.DEFAULT to enable quantization and tf.lite.OpsSet.TFLITE_BUILTINS_INT8 to specify integer-only ops for full quantization support.

5fill in blank

hard

Fill all three blanks to create a pruning schedule with 20% initial sparsity, 80% final sparsity, and pruning ending at step 2000.

MLOps

pruning_params = {
  'pruning_schedule': tfmot.sparsity.keras.PolynomialDecay(initial_sparsity=[1], final_sparsity=[2], begin_step=0, end_step=[3])
}

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

A0.2

B0.8

C2000

D1000

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping initial and final sparsity values.

Using incorrect end step values like 1000 instead of 2000.

The initial sparsity is 20% (0.2), final sparsity is 80% (0.8), and pruning ends at step 2000.