2 [![License](https://img.shields.io/badge/license-BSD-blue.svg)](LICENSE)
4 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.
6 The release version is 0.3.0, is based on [Rockchip RK3399](http://www.rock-chips.com/plus/3399.html) Platform, target OS is Ubuntu 16.04. Can download the source code from [OAID/CaffeOnACL](https://github.com/OAID/CaffeOnACL)
8 * 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).
9 * Caffe is a fast open framework for deep learning. See also [Caffe](https://github.com/BVLC/caffe).
12 * [Installation instructions](https://github.com/OAID/CaffeOnACL/blob/master/acl_openailab/installation.md)
13 * [User Manuals PDF](https://github.com/OAID/CaffeOnACL/blob/master/acl_openailab/user_manual.pdf)
14 * [Performance Report PDF](https://github.com/OAID/CaffeOnACL/blob/master/acl_openailab/performance_report.pdf)
16 ### Arm Compute Library Compatibility Issues :
17 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
19 * Normalization in-channel issue
21 * Softmax supporting multi-dimension issue
24 Performance need be fine turned in the future
27 The Caffe based version is [793bd96351749cb8df16f1581baf3e7d8036ac37](https://github.com/BVLC/caffe/tree/793bd96351749cb8df16f1581baf3e7d8036ac37).
29 ### Version 0.3.0 - Aug 26, 2017
30 Support Arm Compute Library version 17.06 with 4 new layers added
32 * Batch Normalization Layer
33 * Direct convolution Layer
34 * Locally Connect Layer
38 ### Version 0.2.0 - Jul 2, 2017
42 * Compatible with Arm Compute Library version 17.06
43 * When OpenCL initialization fails, even if Caffe uses CPU-mode,it doesn't work properly.
45 ### Version 0.1.0 - Jun 2, 2017
47 Initial version supports 10 Layers accelerated by Arm Compute Library version 17.05 :
61 Encounter any issue, please report on [issue report](https://github.com/OAID/CaffeOnACL/issues). Issue report should contain the following information :
63 * The exact description of the steps that are needed to reproduce the issue
64 * The exact description of what happens and what you think is wrong