Converter command line reference

This page describes how to use the TensorFlow Lite converter using the command line tool. However, the Python API is recommended for the majority of cases.

High-level overview

The TensorFlow Lite Converter has a command line tool named tflite_convert, which supports basic models. Use the Python API for any conversions involving optimizations, or any additional parameters (e.g. signatures in SavedModels or custom objects in Keras models).


The following example shows a SavedModel being converted:

tflite_convert \
  --saved_model_dir=/tmp/mobilenet_saved_model \

The inputs and outputs are specified using the following commonly used flags:

  • --output_file. Type: string. Specifies the full path of the output file.
  • --saved_model_dir. Type: string. Specifies the full path to the directory containing the SavedModel generated in 1.X or 2.X.
  • --keras_model_file. Type: string. Specifies the full path of the HDF5 file containing the tf.keras model generated in 1.X or 2.X.

To use all of the available flags, use the following command:

tflite_convert --help

The following flag can be used for compatibility with the TensorFlow 1.X version of the converter CLI:

  • --enable_v1_converter. Type: bool. Enables user to enable the 1.X command line flags instead of the 2.X flags. The 1.X command line flags are specified here.

Installing the converter CLI

To obtain the latest version of the TensorFlow Lite converter CLI, we recommend installing the nightly build using pip:

pip install tf-nightly

Alternatively, you can clone the TensorFlow repository and use bazel to run the command:

bazel run //tensorflow/lite/python:tflite_convert -- \
  --saved_model_dir=/tmp/mobilenet_saved_model \

Custom ops in the new converter

There is a behavior change in how models containing custom ops (those for which users previously set --allow_custom_ops before) are handled in the new converter.

Built-in TensorFlow op

If you are converting a model with a built-in TensorFlow op that does not exist in TensorFlow Lite, you should set --allow_custom_ops argument (same as before), explained here.

Custom op in TensorFlow

If you are converting a model with a custom TensorFlow op, it is recommended that you write a TensorFlow kernel and TensorFlow Lite kernel. This ensures that the model is working end-to-end, from TensorFlow and TensorFlow Lite. This also requires setting the --allow_custom_ops argument.

Advanced custom op usage (not recommended)

If the above is not possible, you can still convert a TensorFlow model containing a custom op without a corresponding kernel. You will need to pass the OpDef of the custom op in TensorFlow using --custom_opdefs flag, as long as you have the corresponding OpDef registered in the TensorFlow global op registry. This ensures that the TensorFlow model is valid (i.e. loadable by the TensorFlow runtime).

If the custom op is not part of the global TensorFlow op registry, then the corresponding OpDef needs to be specified via the --custom_opdefs flag. This is a list of an OpDef proto in string that needs to be additionally registered. Below is an example of a TFLiteAwesomeCustomOp with 2 inputs, 1 output, and 2 attributes:

--custom_opdefs="name: 'TFLiteAwesomeCustomOp' input_arg: { name: 'InputA'
type: DT_FLOAT } input_arg: { name: ‘InputB' type: DT_FLOAT }
output_arg: { name: 'Output' type: DT_FLOAT } attr : { name: 'Attr1' type:
'float'} attr : { name: 'Attr2' type: 'list(float)'}"