TensorFlow Lite

Headlines · 2

1. 4d
   LiteRT Adds Faster GPU Inference in Google Play Services

   Google announced an upgrade to LiteRT in Google Play services, bringing ML Drift-powered GPU inference to the new CompiledModel API. Google says GPU inference runs about 1.4 times faster than the legacy GPU delegate, while apps that remove their bundled runtime are about 8 MB smaller in its testing. The legacy GPU delegate and custom delegate APIs are deprecated, and NNAPI is scheduled for removal starting in 2027.

   Google Developers Blog · 🔥 0
2. Oct 18
   UCLA's PhoneBot is an open-source humanoid robot that uses old Android phones as its brain

   Researchers at UCLA have developed PhoneBot, an open-source humanoid robot that stands 483 mm tall and weighs 1.8 kg. It uses four tested Android handsets — including a 2017 Honor 9 and three $50–$80 models — for camera-based person tracking, inertial sensing and TensorFlow Lite locomotion control, while a separate onboard computer handles motor communications. The team trained its walking controller with reinforcement learning and mirrored training samples and reported improved gait symmetry; the platform costs about $400 excluding the phone but is limited to flat-ground walking, low-power servos and no arms.

   TechRadar · 🔥 0

Experience and discussion from the community

Share my TensorFlow Lite experienceAsk about TensorFlow Lite