TensorFlow TensorFlow Deployment and TFLite

Question 1

What is TensorFlow Lite (TFLite) designed for?

Accepted Answer

Deploying models on mobile and embedded devices

Answer

Training models faster on desktop GPUs

Answer

Serving models in cloud environments

Answer

Visualizing model architectures

Question 2

What is quantization in TFLite model optimization?

Accepted Answer

Reducing model weight precision (e.g., float32 to int8) to decrease size and improve speed

Answer

Counting model parameters

Answer

Splitting a model into multiple files

Answer

Converting weights to binary format

Question 3

Which class is used to convert a Keras model to TFLite format?

Accepted Answer

tf.lite.TFLiteConverter

Answer

tf.keras.TFLiteExporter

Answer

tf.lite.Converter

Answer

tf.convert.TFLite

Question 4

What is the TensorFlow SavedModel format?

Accepted Answer

A directory containing model architecture, weights, and computation graph

Answer

A single .h5 weight file

Answer

A compressed ZIP archive of model files

Answer

A JSON configuration file

Question 5

What does TensorFlow Serving provide?

Accepted Answer

A production-grade server for serving TensorFlow models via REST and gRPC APIs

Answer

A web dashboard for monitoring models

Answer

A training cluster manager

Answer

A dataset hosting service

Question 6

Which TFLite optimization reduces model size with minimal accuracy loss using magnitude-based pruning?

Accepted Answer

Weight pruning

Answer

Quantization

Answer

Clustering

Answer

Knowledge distillation