The machine learning (ML) models you use with TensorFlow Lite are originally built and trained using TensorFlow core libraries and tools. Once you've built a model with TensorFlow core, you can convert it to a smaller, more efficient ML model format called a TensorFlow Lite model. This page provides guidance for converting your TensorFlow models to the TensorFlow Lite model format.
Converting TensorFlow models to TensorFlow Lite format can take a few paths depending on the content of your ML model. As the first step of that process, you should evaluate your model to determine if it can be directly converted. This evaluation determines if the content of the model is supported by the standard TensorFlow Lite runtime environments based on the TensorFlow operations it uses. If your model uses operations outside of the supported set, you have the option to refactor your model or use advanced conversion techniques.
The diagram below shows the high level steps in converting a model.
Figure 1. TensorFlow Lite conversion workflow.
The following sections outline the process of evaluating and converting models for use with TensorFlow Lite.
Input model formats
You can use the converter with the following input model formats:
- SavedModel (recommended): A TensorFlow model saved as a set of files on disk.
- Keras model: A model created using the high level Keras API.
- Keras H5 format: A light-weight alternative to SavedModel format supported by Keras API.
- Models built from concrete functions: A model created using the low level TensorFlow API.
If you have a Jax model, you can use the
API to convert it to the TensorFlow Lite format. Note that this API is subjct to
change while in experimental mode.
Evaluating your model is an important step before attempting to convert it. When evaluating, you want to determine if the contents of your model is compatible with the TensorFlow Lite format. You should also determine if your model is a good fit for use on mobile and edge devices in terms of the size of data the model uses, its hardware processing requirements, and the model's overall size and complexity.
For many models, the converter should work out of the box. However, TensorFlow Lite builtin operator library supports a subset of TensorFlow core operators, which means some models may need additional steps before converting to TensorFlow Lite. Additionally some operations that are supported by TensorFlow Lite have restricted usage requirements for performance reasons. See the operator compatibility guide to determine if your model needs to be refactored for conversion.
The TensorFlow Lite converter takes a TensorFlow model and generates a
TensorFlow Lite model (an optimized
FlatBuffer format identified by the
.tflite file extension). You can load
a SavedModel or directly convert a model you create in code.
Typically you would convert your model for the standard TensorFlow Lite runtime environment or the Google Play services runtime environment for TensorFlow Lite (Beta). Some advanced use cases require customization of model runtime environment, which require additional steps in the conversion proceess. See the advanced runtime environment section of the Android overview for more guidance.
If you run into errors while running the converter on your model, it's most likely that you have an operator compatibility issue. Not all TensorFlow operations are supported by TensorFlow Lite. You can work around these issues by refactoring your model, or by using advanced conversion options that allow you to create a modified TensorFlow Lite format model and a custom runtime environment for that model.
- See the Model compatibility overview for more information on TensorFlow and TensorFlow Lite model compatibility considerations.
- Topics under the Model compatibility overview cover advanced techniques for refactoring your model, such as the Select operators guide.
- For full list of operations and limitations see TensorFlow Lite Ops page.
- See the optimization overview for guidance on how to optimize your converted model using techniques like post-training quanitization.
- See the Model Analyzer guide to use the API to analyze your model for issues such as delegate compatibility.
- See the Adding metadata overview to learn how to add metadata to your models. Metadata provides other uses a description of your model as well as information that can be leveraged by code generators.