tflite-model-maker 0.2.0

TFLite Model Maker: a model customization library for on-device applications.

TFLite Model Maker

Overview

The TFLite Model Maker library simplifies the process of adapting and converting a TensorFlow neural-network model to particular input data when deploying this model for on-device ML applications.

Requirements

• Refer to requirements.txt for dependent libraries that're needed to use the library and run the demo code.

Installation

There are two ways to install Model Maker.

• Install a prebuilt pip package.

pip install tflite-model-maker

If you want to install nightly version, please follow the command:

pip install tflite-model-maker-nightly

• Clone the source code from GitHub and install.

git clone https://github.com/tensorflow/examples
cd examples/tensorflow_examples/lite/model_maker/pip_package
pip install -e .

End-to-End Example

For instance, it could have an end-to-end image classification example that utilizes this library with just 4 lines of code, each of which representing one step of the overall process. For more detail, you could refer to Colab for image classification.

1. Load input data specific to an on-device ML app.

data = ImageClassifierDataLoader.from_folder('flower_photos/')

2. Customize the TensorFlow model.

model = image_classifier.create(data)

3. Evaluate the model.

loss, accuracy = model.evaluate()

4. Export to Tensorflow Lite model and label file in export_dir.

model.export(export_dir='/tmp/')

Notebook

Currently, we support image classification, text classification and question answer tasks. Meanwhile, we provide demo code for each of them in demo folder.

• Overview for Tensorflow Lite Model Maker
• Colab for image classification
• Colab for text classification
• Colab for question answer