在移动设备和 IoT 设备上部署机器学习模型
TensorFlow Lite 是一种用于设备端推断的开源深度学习框架。
Use a state-of-the-art natural language model to answer questions based on the content of a given passage of text with BERT.
我们的一些 TensorFlow Lite 用户
It's incredible what you can do with a phone camera, TensorFlow and a bit of imagination.
In this episode of Inside TensorFlow, Software Engineer Yu-Cheng Ling demonstrates the new TF Lite Converter, discussing why it’s important and how to use it.
Use Firebase to update TensorFlow Lite models without app updates, A/B test multiple model versions in production, and measure inference speed on user devices.
TensorFlow Lite runs on more than 4 billion active devices globally on various platforms. We continue to push the limits of on-device machine learning by making it faster and easier to use.