Model optimization for serving (quantization, pruning) in MLOps - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding Quantization Impact

Which of the following best describes the main benefit of quantization in model serving?

A It increases model accuracy by adding more layers.

B It removes unnecessary neurons to simplify the model architecture.

C It converts the model to a different programming language for compatibility.

D It reduces model size and speeds up inference by using lower precision numbers.

💡 Hint

Think about how using smaller numbers affects memory and speed.

Quantization reduces the precision of numbers used in the model (e.g., from 32-bit floats to 8-bit integers), which makes the model smaller and faster to run without changing its structure.

💻 Command Output

intermediate

Output of Pruning Command

What is the expected output after running this pruning command on a TensorFlow model?

MLOps

tfmot.sparsity.keras.prune_low_magnitude(model, pruning_schedule=tfmot.sparsity.keras.PolynomialDecay(initial_sparsity=0.0, final_sparsity=0.5, begin_step=0, end_step=1000))

A A pruned model with approximately 50% of weights set to zero after 1000 steps.

B A model converted to 8-bit integers for faster inference.

C An error because pruning requires a different API call.

D A model with all weights doubled in magnitude.

💡 Hint

Pruning gradually removes weights by setting them to zero based on magnitude.

The pruning schedule gradually increases sparsity from 0% to 50% over 1000 steps, zeroing out small weights to reduce model size and computation.

🔀 Workflow

advanced

Correct Sequence for Model Quantization Workflow

Arrange the steps in the correct order to perform post-training quantization for a TensorFlow model.

A 2,1,3,4

B 1,2,3,4

C 1,3,2,4

D 1,2,4,3

💡 Hint

Think about loading first, then converting, saving, and finally testing.

The workflow starts by loading the original model, then converting it with quantization, saving the new model, and finally testing it to ensure quality.

❓ Troubleshoot

advanced

Troubleshooting Accuracy Drop After Pruning

After pruning a model, you notice a significant drop in accuracy. Which option is the most likely cause?

A The pruning API was not called, so the model was unchanged.

B The model was quantized instead of pruned, causing precision loss.

C The pruning sparsity was set too high too quickly, removing important weights.

D The model was trained with too many epochs before pruning.

💡 Hint

Consider how pruning speed and amount affect model quality.

Pruning too aggressively or too fast can remove weights that are important for accuracy, causing the model to perform worse.

✅ Best Practice

expert

Best Practice for Combining Quantization and Pruning

Which practice is recommended when combining pruning and quantization to optimize a model for serving?

A First prune the model to reduce weights, then fine-tune it, and finally apply quantization.

B Apply quantization first, then prune the quantized model without retraining.

C Prune and quantize simultaneously without any fine-tuning steps.

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

💡 Hint

Think about the order that preserves accuracy and model size reduction.

Pruning first reduces the model size by removing weights, then fine-tuning recovers accuracy, and finally quantization reduces precision for faster inference.