Google porta il supporto Nucleo ML a tensorflow Lite

Google today released a tool that converts Apple’s Core ML .mlmodel file format into .tflite for use with TensorFlow Lite, una versione del programma di open source di Google per la formazione e l'implementazione di modelli di intelligenza artificiale.

Il convertitore è stato realizzato in collaborazione con Apple, according to a Google developers post del Blog.

Like TensorFlow Lite, Core ML gives developers a framework to quickly add AI services like object identification or natural language processing to apps.

TensorFlow Lite developer preview for makers of iOS and Android apps was first made available last month. Created especially for the deployment of AI in mobile devices, TensorFlow Lite comes prepared to deploy some premade models, such as MobileNet and Inception-v3 for object identification with computer vision and Smart Reply for suggested responses.

Entrambi Core ML e TensorFlow Lite were announced this spring at respective developer conferences for Google and Apple.

Articolo originale

Nessun tag per questo post.