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'.