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
andinference_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.
- Support integer (previously, only float) input/output type for integer
quantized models using the new
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 totarget_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 thetf.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.
- quantization:
- Removed other converter APIs such as
tf.lite.toco_convert
andtf.lite.TocoConverter
- Removed other related APIs such as
tf.lite.OpHint
andtf.lite.constants
(thetf.lite.constants.*
types have been mapped totf.*
TensorFlow data types, to reduce duplication)
- Renamed the