From 485eec2a473e0a1804f59f6254f28a591197878e Mon Sep 17 00:00:00 2001 From: xuhaibing Date: Sun, 24 Sep 2017 22:50:43 +0800 Subject: [PATCH] Update release_notes.md --- acl_openailab/release_notes.md | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/acl_openailab/release_notes.md b/acl_openailab/release_notes.md index 4195b65..8c8afc7 100644 --- a/acl_openailab/release_notes.md +++ b/acl_openailab/release_notes.md @@ -1,6 +1,4 @@ - - -# Release Note +# 1. Release Note [![License](https://img.shields.io/badge/license-BSD-blue.svg)](LICENSE) CaffeOnACL is a project that is maintained by **OPEN** AI LAB, it uses Arm Compute Library (NEON+GPU) to speed up [Caffe](http://caffe.berkeleyvision.org/) and provide utilities to debug, profile and tune application performance. @@ -10,17 +8,20 @@ The release version is 0.3.0, is based on Rockchip RK3399 Platform, target OS is * The ARM Computer Vision and Machine Learning library is a set of functions optimised for both ARM CPUs and GPUs using SIMD technologies. See also [Arm Compute Library](https://github.com/ARM-software/ComputeLibrary). * Caffe is a fast open framework for deep learning. See also [Caffe](https://github.com/BVLC/caffe). -## Verified Platform : - -Verified on ARMv8 processor. - +## 1.1 Verified Platform : - Hardware platform : Rockchip RK3399. See also [RK3399 SoC](http://www.rock-chips.com/plus/3399.html) - Software platform : Ubuntu 16.04 -## Installation +## 1.2 Installation (Quick User Guide) Please refer to [Installation](installation.md) for details -## Arm Compute Library Compatibility Issues : +## 1.3 User Manual +Please refer to [Performance Report](performance_report.pdf) for details + +## 1.4 Performance Report +Please refer to [Performance Report](performance_report.pdf) for details + +## 1.5 Arm Compute Library Compatibility Issues : There are some compatibility issues between ACL and Caffe Layers, we bypass it to Caffe's original layer class as the workaround solution for the below issues * Normalization in-channel issue @@ -30,18 +31,18 @@ There are some compatibility issues between ACL and Caffe Layers, we bypass it t Performance need be fine turned in the future -# Issue Report +# 2 Issue Report Encounter any issue, please report on [issue report](https://github.com/OAID/CaffeOnACL/issues). Issue report should contain the following information : * The exact description of the steps that are needed to reproduce the issue * The exact description of what happens and what you think is wrong -## Release History +# 3 Release History The Caffe based version is [793bd96351749cb8df16f1581baf3e7d8036ac37](https://github.com/BVLC/caffe/tree/793bd96351749cb8df16f1581baf3e7d8036ac37). -## CaffeOnACL Version 0.3.0 - Aug 26, 2017 +## 3.1 CaffeOnACL Version 0.3.0 - Aug 26, 2017 Support Arm Compute Library version 17.06 with 4 new layers added @@ -51,7 +52,7 @@ Support Arm Compute Library version 17.06 with 4 new layers added * Concatenate layer -## CaffeOnACL Version 0.2.0 - Jul 2, 2017 +## 3.2 CaffeOnACL Version 0.2.0 - Jul 2, 2017 Fix the issues: @@ -60,7 +61,7 @@ Fix the issues: -## CaffeOnACL Version 0.1.0 - Jun 2, 2017 +## 3.3 CaffeOnACL Version 0.1.0 - Jun 2, 2017 Initial version supports 10 Layers accelerated by Arm Compute Library version 17.05 : -- 2.7.4