project_path: /lite/_project.yaml book_path: /lite/_book.yaml description: landing_page: custom_css_path: /site-assets/css/style.css rows: - heading: TensorFlow Lite is for mobile and embedded devices. description: >

TensorFlow Lite is the official solution for running machine learning models on mobile and embedded devices. It enables on‑device machine learning inference with low latency and a small binary size on Android, iOS, and other operating systems.

- classname: tfo-landing-row-heading tfo-landing-row-heading-list heading: Many benefits description: > On-device ML inference is difficult because of the many constraints—TensorFlow Lite can solve these: items: - list: - heading: Performance description: > TF Lite is fast with no noticeable accuracy loss—see the metrics. icon: icon_name: lens foreground: theme - heading: Portability description: > Android, iOS, and more specialized IoT devices. icon: icon_name: lens foreground: theme - list: - heading: Low latency description: > Optimized float- and fixed-point CPU kernels, op‑fusing, and more. icon: icon_name: lens foreground: theme - heading: Acceleration description: > Integration with GPU and internal/external accelerators. icon: icon_name: lens foreground: theme - list: - heading: Small model size description: > Controlled dependencies, quantization, and op registration. icon: icon_name: lens foreground: theme - heading: Tooling description: > Conversion, compression, benchmarking, power-consumption, and more. icon: icon_name: lens foreground: theme - classname: devsite-landing-row-logos tfo-landing-row-heading heading: Companies using TensorFlow Lite items: - custom_image: path: ./images/landing-page/photos_logo.png path: https://www.photos.google.com - custom_image: path: ./images/landing-page/gboard_logo.png path: https://play.google.com/store/apps/details?id=com.google.android.inputmethod.latin&hl=en_US - custom_image: path: ./images/landing-page/gmail_logo.png path: https://www.google.com/gmail/ - custom_image: path: ./images/landing-page/assistant_logo.png path: https://assistant.google.com/ - classname: devsite-landing-row-logos items: - custom_image: path: ./images/landing-page/vsco_logo.png path: https://vsco.co - custom_image: path: ./images/landing-page/shazam_logo.png path: https://www.shazam.com/ - custom_image: path: ./images/landing-page/nest_logo.png path: https://nest.com/ - custom_image: path: ./images/landing-page/loseit_logo.png path: https://www.loseit.com/ - classname: devsite-landing-row-no-image-background devsite-landing-row-67 background: grey items: - description: > “TensorFlow Lite helped us introduce machine learning and AI into our app in an easy and streamlined way. We could reduce the size of our models while keeping the accuracy high. This helped us create an amazing fishing experience for our users by allowing them to identify any fish species with just a photo.” image_path: ./images/landing-page/fishbrain_logo_big.png - heading: How it works items: - heading: Build icon: icon_name: build description: > Build a new model or retrain an existing one, such as using transfer learning. buttons: - label: Read the developer guide path: /lite/devguide classname: button button-primary tfo-button-primary - heading: Convert icon: icon_name: autorenew description: > Convert a TensorFlow model into a compressed flat buffer with the TensorFlow Lite Optimizing Converter (TOCO). buttons: - label: Read the TOCO guide path: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/lite/toco/g3doc/python_api.md classname: button button-primary tfo-button-primary - heading: Deploy icon: icon_name: bolt description: > Take the compressed .tflite file and load it into a mobile or embedded device.
See the tutorials below to build an app. - heading: Build your first TensorFlow Lite app background: grey items: - classname: tfo-landing-row-item-inset-white heading: Get started description: > - classname: tfo-landing-row-item-inset-white heading: Share your TensorFlow Lite story description: > We love to hear what you're working on—it may even get highlighted on our social media! Tell us. - classname: devsite-landing-row-no-image-background devsite-landing-row-67 items: - description: >

“The release of TensorFlow Lite has allowed us to deploy an engaging real-time experience to our users that eliminates the requirement for a data connection. TensorFlow Lite’s ability to compress and optimize the TensorFlow graph for mobile deployment has been transformative in expanding the capabilities of Snap It.

Through TensorFlow Lite, our users can now enjoy a state of the art, computer-vision-based food logging experience without worrying about signal strength. We look forward to future collaborations with the TensorFlow Lite team.”

image_path: ./images/landing-page/loseit_logo_big.png - classname: devsite-landing-row-cards background: grey heading: Updates items: - heading: Introducing the Model Optimization Toolkit image_path: /ecosystem/images/tf-logo-card-16x9.png path: https://medium.com/tensorflow/introducing-the-model-optimization-toolkit-for-tensorflow-254aca1ba0a3 buttons: - label: Read on TensorFlow blog path: https://medium.com/tensorflow/introducing-the-model-optimization-toolkit-for-tensorflow-254aca1ba0a3 - heading: East Africa Cassava App image_path: ./images/landing-page/detect_crop_disease_in_africa.png path: https://heartbeat.fritz.ai/community-spotlight-nuru-a-mobile-app-by-plantvillage-to-detect-crop-disease-in-africa-28d142bf63d5 buttons: - label: Read more path: https://heartbeat.fritz.ai/community-spotlight-nuru-a-mobile-app-by-plantvillage-to-detect-crop-disease-in-africa-28d142bf63d5 - heading: Using TensorFlow Lite on Android image_path: /ecosystem/images/tf-logo-card-16x9.png path: https://medium.com/tensorflow/using-tensorflow-lite-on-android-9bbc9cb7d69d buttons: - label: Read on TensorFlow blog path: https://medium.com/tensorflow/using-tensorflow-lite-on-android-9bbc9cb7d69d - classname: devsite-landing-row-cards background: grey items: - heading: TensorFlow Lite at the Dev Summit youtube_id: FAMfy7izB6A buttons: - label: Watch the video path: https://www.youtube.com/watch?v=FAMfy7izB6A - heading: TensorFlow Lite on GitHub image_path: /ecosystem/images/github-card-16x9.png path: https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/lite buttons: - label: View on GitHub path: https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/lite - classname: devsite-landing-row-item-hidden