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

tf.lite.Interpreter

View source on GitHub

Interpreter interface for running TensorFlow Lite models.

tf.lite.Interpreter(
    model_path=None,
    model_content=None,
    experimental_delegates=None,
    num_threads=None,
    experimental_op_resolver_type=tf.lite.experimental.OpResolverType.AUTO,
    experimental_preserve_all_tensors=False,
    experimental_disable_delegate_clustering=False,
    experimental_default_delegate_latest_features=False
)

Used in the notebooks

Used in the guide	Used in the tutorials
Signatures in TensorFlow Lite Cluster preserving quantization aware training (CQAT) Keras example Pruning preserving quantization aware training (PQAT) Keras example Weight clustering in Keras example Sparsity and cluster preserving quantization aware training (PCQAT) Keras example	Post-training integer quantization Jax Model Conversion For TFLite On-Device Training with TensorFlow Lite Artistic Style Transfer with TensorFlow Lite Post-training float16 quantization

Models obtained from TfLiteConverter can be run in Python with Interpreter.

As an example, let's generate a simple Keras model and convert it to TFLite (TfLiteConverter also supports other input formats with from_saved_model and from_concrete_function)

x = np.array([[1.], [2.]])
y = np.array([[2.], [4.]])
model = tf.keras.models.Sequential([
          tf.keras.layers.Dropout(0.2