Tensorflow Lite

TensorFlow Lite is for mobile and embedded devices.

Tensorflow Lite 是针对移动和嵌入式设备的

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.

TF lite是针对在移动和嵌入式设备上运行机器学习模型的官方解决方案。

支持在Android，IOS和其他操作系统的设备上以低延迟和小的二进制大小进行机器学习推理。

 

Many benefits  诸多优势

On-device ML inference is difficult because of the many constraints—TensorFlow Lite can solve these:

基于设备的ML推理是困难的，由于很多限制——TF lite可以解决这些：

• Performance 性能

  TF Lite is fast with no noticeable accuracy loss—see the metrics.   没有明显的精度损失同时很快

• Portability  可移植性

  Android, iOS, and more specialized IoT devices. 安卓，IOS和更多特殊的IOT设备

• Low latency  低延迟

  Optimized float- and fixed-point CPU kernels, op‑fusing, and more.

• Acceleration  加速

  Integration with GPU and internal/external accelerators.

• Small model size 模型尺寸变小

  Controlled dependencies, quantization, and op registration. 控制依赖、量化、op注册

• Tooling 工具

  Conversion, compression, benchmarking, power-consumption, and more. 转换，压缩，基准，能量损耗等

 

 

How it works

 

Build

Build a new model or retrain an existing one, such as using transfer learning.

 

Convert

Convert a TensorFlow model into a compressed flat buffer with the TensorFlow Lite Converter.

 

Deploy

Take the compressed .tflite file and load it into a mobile or embedded device.
See the tutorials below to build an app.