Module: tflite_model_maker

Public APIs for TFLite Model Maker, a transfer learning library to train custom TFLite models.

You can install the package with

pip install tflite-model-maker

Typical usage of Model Maker is to create a model in a few lines of code, e.g.:

# Load input data specific to an on-device ML app.
data = DataLoader.from_folder('flower_photos/')
train_data, test_data = data.split(0.9)

# Customize the TensorFlow model.
model = image_classifier.create(train_data)

# Evaluate the model.
accuracy = model.evaluate(test_data)

# Export to Tensorflow Lite model and label file in `export_dir`.

For more details, please refer to our guide:


audio_classifier module: APIs to train an audio classification model.

config module: APIs for the config of TFLite Model Maker.

image_classifier module: APIs to train an image classification model.

model_spec module: APIs for the model spec of TFLite Model Maker.

object_detector module: APIs to train an object detection model.

question_answer module: APIs to train a model that can answer questions based on a predefined text.

recommendation module: APIs to train an on-device recommendation model.

searcher module: APIs to create the searcher model.

text_classifier module: APIs to train a text classification model.

version '0.4.2'