diff --git a/README.md b/README.md index 43bd66e4433f99517b43316631b346c707cb113e..5c48b5eefcbea203e4830170b9d847bd4be59a53 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,7 @@ [中文](README_zh.md) **Mobile AI Compute Engine** (or **MACE** for short) is a deep learning inference framework optimized for -mobile heterogeneous computing platforms. The design focuses on the following +mobile heterogeneous computing on Android, iOS and Linux devices. The design focuses on the following targets: * Performance * Runtime is optimized with NEON, OpenCL and Hexagon, and @@ -41,8 +41,7 @@ targets: code and literal obfuscations. * Platform coverage * Good coverage of recent Qualcomm, MediaTek, Pinecone and other ARM based - chips. CPU runtime is also compatible with most POSIX systems and - architectures with limited performance. + chips. CPU runtime supports Android, iOS and Linux. * Rich model formats support * [TensorFlow](https://github.com/tensorflow/tensorflow), [Caffe](https://github.com/BVLC/caffe) and diff --git a/README_zh.md b/README_zh.md index c63a0c71a4fd3a8a69624bd2532991fd557912d7..b315f87042a4c6cd3601ad7eca2f9c47b6d288bb 100644 --- a/README_zh.md +++ b/README_zh.md @@ -15,7 +15,7 @@ [加入我们](JOBS.md) | [English](README.md) -**Mobile AI Compute Engine (MACE)** 是一个专为移动端异构计算平台优化的神经网络计算框架。 +**Mobile AI Compute Engine (MACE)** 是一个专为移动端异构计算平台(支持Android, iOS, Linux)优化的神经网络计算框架。 主要从以下的角度做了专门的优化: * 性能 * 代码经过NEON指令,OpenCL以及Hexagon HVX专门优化,并且采用 @@ -32,8 +32,7 @@ * 模型加密与保护 * 模型保护是重要设计目标之一。支持将模型转换成C++代码,以及关键常量字符混淆,增加逆向的难度。 * 硬件支持范围 - * 支持高通,联发科,以及松果等系列芯片的CPU,GPU与DSP(目前仅支持Hexagon)计算加速。 - 同时支持在具有POSIX接口的系统的CPU上运行。 + * 支持高通,联发科,以及松果等系列芯片的CPU,GPU与DSP(目前仅支持Hexagon)计算加速。CPU模式支持Android, iOS, Linux等系统。 * 模型格式支持 * 支持[TensorFlow](https://github.com/tensorflow/tensorflow), [Caffe](https://github.com/BVLC/caffe)和[ONNX](https://github.com/onnx/onnx)等模型格式。