Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more

tf.lite.TFLiteConverter

View source on GitHub

Converts a TensorFlow model into TensorFlow Lite model.

tf.lite.TFLiteConverter(
    funcs, trackable_obj=None
)

Used in the notebooks

Used in the guide	Used in the tutorials
TensorFlow Lite Model Analyzer Signatures in TensorFlow Lite TFLite Authoring Tool Migrating your TFLite code to TF2 Cluster preserving quantization aware training (CQAT) Keras example	Post-training integer quantization Setup Inspecting Quantization Errors with Quantization Debugger Jax Model Conversion For TFLite Post-training dynamic range quantization

Example usage:

# Converting a SavedModel to a TensorFlow Lite model.
converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
tflite_model = converter.convert()

# Converting a tf.Keras model to a TensorFlow Lite model.
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()