TensorFlow Model Optimization

Learn the latest in machine learning, generative AI, and more at WiML Symposium 2023Register

Optimize machine learning models

import tensorflow as tf
import tensorflow_model_optimization as tfmot

model = tf.keras.Sequential([...])

pruning_schedule = tfmot.sparsity.keras.PolynomialDecay(
                      initial_sparsity=0.0, final_sparsity=0.5,
                      begin_step=2000, end_step=4000)

model_for_pruning = tfmot.sparsity.keras.prune_low_magnitude(
    model, pruning_schedule=pruning_schedule)
...

model_for_pruning.fit(...)

The TensorFlow Model Optimization Toolkit is a suite of tools for optimizing ML models for deployment and execution. Among many uses, the toolkit supports techniques used to:

Reduce latency and inference cost for cloud and edge devices (e.g. mobile, IoT).
Deploy models to edge devices with restrictions on processing, memory, power-consumption, network usage, and model storage space.
Enable execution on and optimize for existing hardware or new special purpose accelerators.

Choose the model and optimization tool depending on your task:

Improve performance with off-the-shelf models

In many cases, pre-optimized models can improve the efficiency of your application.
Use the TensorFlow Model Optimization Toolkit

Try the post-training tools to optimize an already-trained TensorFlow model.
Optimize further

Use training-time optimization tools and learn about the techniques.