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。
我们的一些 TensorFlow Lite 用户
Example on-device model personalization with TensorFlow Lite
Try out a new on-device transfer learning image classification example.
Track human poses in real-time on Android
Build a human pose estimation app by detecting the positions of key body parts such as the position of a person’s elbows and/or knees.
Introducing float16 quantization for the Model Optimization Toolkit
Post-training float16 quantization reduces TensorFlow Lite model sizes up to 50% while sacrificing very little accuracy - and is great for GPUs!