TensorFlow Lite example apps

Explore pre-trained TensorFlow Lite models and learn how to use them in sample apps for a variety of ML applications.

Autocomplete

Generate suggestions for text inputs using a Keras language model.

Image classification

Identify hundreds of objects, including people, activities, animals, plants, and places.

Object detection

Detect multiple objects with bounding boxes. Yes, dogs and cats too.

Pose estimation

Estimate poses for single or multiple people. Imagine the possibilities, including stick figure dance parties.

Speech recognition

Identify speech commands by recognizing keywords.

Segmentation

Pinpoint the shape of objects with strict localization accuracy and semantic labels. Trained with people, places, animals, and more.

Text classification

Categorize free text into predefined groups. Potential applications include abusive content moderation, tone detection, and more.

On-device recommendation

Provide personalized on-device recommendations based on events selected by users.

Natural language question answering

Answer questions based on the content of a given passage of text with BERT.

Style transfer

Apply any styles on an input image to create a new artistic image.

Smart reply

Generate reply suggestions to input conversational chat messages.

Super resolution

Generate a super resolution image from a low resolution image.

Reinforcement learning

Train a game agent using reinforcement learning and build an Android game using TensorFlow Lite.

Optical character recognition

Extract texts from images using Optical Character Recognition with TensorFlow Lite.

On-device training

Train a TensorFlow Lite model on-device.