Apply to speak at TensorFlow World. Deadline April 23rd. Propose talk

Get started with TensorFlow Lite

Using a TensorFlow Lite model in your mobile app requires multiple considerations: you must choose a pre-trained or custom model, convert the model to a TensorFLow Lite format, and finally, integrate the model in your app.

1. Choose a model

Depending on the use case, you can choose one of the popular open-sourced models, such as InceptionV3 or MobileNets, and re-train these models with a custom data set or even build your own custom model.

Use a pre-trained model

MobileNets is a family of mobile-first computer vision models for TensorFlow designed to effectively maximize accuracy, while taking into consideration the restricted resources for on-device or embedded applications. MobileNets are small, low-latency, low-power models parameterized to meet the resource constraints for a variety of uses. They can be used for classification, detection, embeddings, and segmentation—similar to other popular large scale models, such as Inception. Google provides 16 pre-trained ImageNet classification checkpoints for MobileNets that can be used in mobile projects of all sizes.

Inception-v3 is an image recognition model that achieves fairly high accuracy recognizing general objects with 1000 classes, for example, "Zebra", "Dalmatian", and "Dishwasher". The model extracts general features from input images using a convolutional neural network and classifies them based on those features with fully-connected and softmax layers.

On Device Smart Reply is an on-device model that provides one-touch replies for incoming text messages by suggesting contextually relevant messages. The model is built specifically for memory constrained devices, such as watches and phones, and has been successfully used in Smart Replies on Android Wear. Currently, this model is Android-specific.

These pre-trained models are available for download.

Re-train Inception-V3 or MobileNet for a custom data set

These pre-trained models were trained on the ImageNet data set which contains 1000 predefined classes. If these classes are not sufficient for your use case, the model will need to be re-trained. This technique is called transfer learning and starts with a model that has been already trained on a problem, then retrains the model on a similar problem. Deep learning from scratch can take days, but transfer learning is fairly quick. In order to do this, you need to generate a custom data set labeled with the relevant classes.

The TensorFlow for Poets codelab walks through the re-training process step-by-step. The code supports both floating point and quantized inference.

Train a custom model

A developer may choose to train a custom model using Tensorflow (see the TensorFlow tutorials for examples of building and training models). If you have already written a model, the first step is to export this to a tf.GraphDef file. This is required because some formats do not store the model structure outside the code, and we must communicate with other parts of the framework. See Exporting the Inference Graph to create file for the custom model.

TensorFlow Lite currently supports a subset of TensorFlow operators. Refer to the TensorFlow Lite & TensorFlow Compatibility Guide for supported operators and their usage. This set of operators will continue to grow in future Tensorflow Lite releases.

2. Convert the model format

The TensorFlow Lite Converter accepts the following file formats:

  • SavedModel — A GraphDef and checkpoint with a signature that labels input and output arguments to a model. See the documentation for converting SavedModels using Python or using the command line.
  • tf.keras - A HDF5 file containing a model with weights and input and output arguments generated by tf.Keras. See the documentation for converting HDF5 models using Python or using the command line.
  • frozen tf.GraphDef — A subclass of tf.GraphDef that does not contain variables. A GraphDef can be converted to a frozen GraphDef by taking a checkpoint and a GraphDef, and converting each variable into a constant using the value retrieved from the checkpoint. Instructions on converting a tf.GraphDef to a TensorFlow Lite model are described in the next subsection.

Converting a tf.GraphDef

TensorFlow models may be saved as a .pb or .pbtxt tf.GraphDef file. In order to convert the tf.GraphDef file to TensorFlow Lite, the model must first be frozen. This process involves several file formats including the frozen GraphDef:

  • tf.GraphDef (.pb or .pbtxt) — A protobuf that represents the TensorFlow training or computation graph. It contains operators, tensors, and variables definitions.
  • checkpoint (.ckpt) — Serialized variables from a TensorFlow graph. Since this does not contain a graph structure, it cannot be interpreted by itself.
  • TensorFlow Lite model (.tflite) — A serialized FlatBuffer that contains TensorFlow Lite operators and tensors for the TensorFlow Lite interpreter.

You must have checkpoints that contain trained weights. The tf.GraphDef file only contains the structure of the graph. The process of merging the checkpoint values with the graph structure is called freezing the graph.

tf.GraphDef and checkpoint files for MobileNet models are available here.

To freeze the graph, use the following command (changing the arguments):

freeze_graph --input_graph=/tmp/mobilenet_v1_224.pb \
  --input_checkpoint=/tmp/checkpoints/mobilenet-10202.ckpt \
  --input_binary=true \
  --output_graph=/tmp/frozen_mobilenet_v1_224.pb \

Set the input_binary flag to True when reading a binary protobuf, a .pb file. Set to False for a .pbtxt file.

Set input_graph and input_checkpoint to the respective filenames. The output_node_names may not be obvious outside of the code that built the model. The easiest way to find them is to visualize the graph, either with TensorBoard or graphviz.

The frozen GraphDef is now ready for conversion to the FlatBuffer format (.tflite) for use on Android or iOS devices. For Android, the TensorFlow Lite Converter tool supports both float and quantized models. To convert the frozen GraphDef to the .tflite format use a command similar to the following:

tflite_convert \
  --output_file=/tmp/mobilenet_v1_1.0_224.tflite \
  --graph_def_file=/tmp/mobilenet_v1_0.50_128/frozen_graph.pb \
  --input_arrays=input \

The frozen_graph.pb file used here is available for download. Setting the input_array and output_array arguments is not straightforward. The easiest way to find these values is to explore the graph using TensorBoard. Reuse the arguments for specifying the output nodes for inference in the freeze_graph step.

Full converter reference

The TensorFlow Lite Converter can be Python or from the command line. This allows you to integrate the conversion step into the model design workflow, ensuring the model is easy to convert to a mobile inference graph.

Ops compatibility

Refer to the ops compatibility guide for troubleshooting help, and if that doesn't help, please file an issue.

Graph Visualization tool

The development repo contains a tool to visualize TensorFlow Lite models after conversion. To build the tool:

bazel run tensorflow/lite/tools:visualize -- model.tflite model_viz.html

This generates an interactive HTML page listing subgraphs, operations, and a graph visualization.

3. Use the TensorFlow Lite model for inference in a mobile app

After completing the prior steps, you should now have a .tflite model file.


Since Android apps are written in Java and the core TensorFlow library is in C++, a JNI library is provided as an interface. This is only meant for inference—it provides the ability to load a graph, set up inputs, and run the model to calculate outputs.

The open source Android demo app uses the JNI interface and is available on GitHub. You can also download a prebuilt APK. See the Android demo guide for details.

The Android mobile guide has instructions for installing TensorFlow on Android and setting up bazel and Android Studio.


To integrate a TensorFlow model in an iOS app, see the TensorFlow Lite for iOS guide and iOS demo guide.

Core ML support

Core ML is a machine learning framework used in Apple products. In addition to using Tensorflow Lite models directly in your applications, you can convert trained Tensorflow models to the CoreML format for use on Apple devices. To use the converter, refer to the Tensorflow-CoreML converter documentation.

ARM32 and ARM64 Linux

Compile Tensorflow Lite for a Raspberry Pi by following the RPi build instructions Compile Tensorflow Lite for a generic aarch64 board such as Odroid C2, Pine64, NanoPi, and others by following the ARM64 Linux build instructions This compiles a static library file (.a) used to build your app. There are plans for Python bindings and a demo app.

4. Optimize your model (optional)

There are two options. If you plan to run on CPU, we recommend that you quantize your weights and activation tensors. If the hardware is available, another option is to run on GPU for massively parallelizable workloads.


Compress your model size by lowering the precision of the parameters (i.e. neural network weights) from their training-time 32-bit floating-point representations into much smaller and efficient 8-bit integer ones.

This will execute the heaviest computations fast in lower precision, but the most sensitive ones with higher precision, thus typically resulting in little to no final accuracy losses for the task, yet a significant speed-up over pure floating-point execution.

The post-training quantization technique is integrated into the TensorFlow Lite conversion tool. Getting started is easy: after building your TensorFlow model, simply enable the ‘post_training_quantize’ flag in the TensorFlow Lite conversion tool. Assuming that the saved model is stored in saved_model_dir, the quantized tflite flatbuffer can be generated in command line:

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
converter.optimizations = [tf.lite.Optimize.OPTIMIZE_FOR_SIZE]
tflite_quant_model = converter.convert()

Read the full documentation here and see a tutorial here.


Run on GPU GPUs are designed to have high throughput for massively parallelizable workloads. Thus, they are well-suited for deep neural nets, which consist of a huge number of operators, each working on some input tensor(s) that can be easily divided into smaller workloads and carried out in parallel, typically resulting in lower latency.

Another benefit with GPU inference is its power efficiency. GPUs carry out the computations in a very efficient and optimized manner, so that they consume less power and generate less heat than when the same task is run on CPUs.

Read the tutorial here and full documentation here.