API Updates

This page provides information about updates made to the tf.lite.TFLiteConverter Python API in TensorFlow 2.x.

• TensorFlow 2.3

  • Support integer (previously, only float) input/output type for integer quantized models using the new inference_input_type and inference_output_type attributes. Refer to this example usage.
  • Support conversion and resizing of models with dynamic dimensions.
  • Added a new experimental quantization mode with 16-bit activations and 8-bit weights.

• TensorFlow 2.2

  • By default, leverage MLIR-based conversion, Google's cutting edge compiler technology for machine learning. This enables conversion of new classes of models, including Mask R-CNN, Mobile BERT, etc and supports models with functional control flow.

• TensorFlow 2.0 vs TensorFlow 1.x

  • Renamed the target_ops attribute to target_spec.supported_ops
  • Removed the following attributes:
    • quantization: inference_type, quantized_input_stats, post_training_quantize, default_ranges_stats, reorder_across_fake_quant, change_concat_input_ranges, get_input_arrays(). Instead, quantize aware training is supported through the tf.keras API and post training quantization uses fewer attributes.
    • visualization: output_format, dump_graphviz_dir, dump_graphviz_video. Instead, the recommended approach for visualizing a TensorFlow Lite model is to use visualize.py.
    • frozen graphs: drop_control_dependency, as frozen graphs are unsupported in TensorFlow 2.x.
  • Removed other converter APIs such as tf.lite.toco_convert and tf.lite.TocoConverter
  • Removed other related APIs such as tf.lite.OpHint and tf.lite.constants (the tf.lite.constants.* types have been mapped to tf.* TensorFlow data types, to reduce duplication)