path: root/
diff options
authorxuhaibing <>2017-09-24 15:45:56 (GMT)
committerxuhaibing <>2017-09-24 15:45:56 (GMT)
commit79a676c5beb7eb703ded4114df69b3f717f9e933 (patch)
tree0c5b71e50836a2fa24548efe4c7e8be8dc2e5281 /
parentc6fa1d4a168d3a34ca1bc256a01b8d0d4dc15946 (diff)
change reademe
Diffstat (limited to '')
1 files changed, 52 insertions, 25 deletions
diff --git a/ b/
index 44b9e62..3d3b597 100644
--- a/
+++ b/
@@ -1,37 +1,64 @@
-# Caffe
-[![Build Status](](
+# CaffeOnACL
-Caffe is a deep learning framework made with expression, speed, and modularity in mind.
-It is developed by the Berkeley Vision and Learning Center ([BVLC]( and community contributors.
+CaffeOnACL is a project that is maintained by **OPEN** AI LAB, it uses Arm Compute Library (NEON+GPU) to speed up [Caffe]( and provide utilities to debug, profile and tune application performance.
+The release version is 0.3.0, is based on [Rockchip RK3399]( Platform, target OS is Ubuntu 16.04. Can download the source code from [OAID/CaffeOnACL](
+* 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](
+* Caffe is a fast open framework for deep learning. See also [Caffe](
+### Documents
+* [Installation instructions](
+* [User Manuals PDF](
+* [Performance Report PDF](
+### 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
+* Tanh issue
+* Softmax supporting multi-dimension issue
+* Group issue
+Performance need be fine turned in the future
+# Release History
+The Caffe based version is [793bd96351749cb8df16f1581baf3e7d8036ac37](
-Check out the [project site]( for all the details like
+### Version 0.3.0 - Aug 26, 2017
+Support Arm Compute Library version 17.06 with 4 new layers added
-- [DIY Deep Learning for Vision with Caffe](
-- [Tutorial Documentation](
-- [BVLC reference models]( and the [community model zoo](
-- [Installation instructions](
+* Batch Normalization Layer
+* Direct convolution Layer
+* Locally Connect Layer
+* Concatenate layer
-and step-by-step examples.
-[![Join the chat at](](
+### Version 0.2.0 - Jul 2, 2017
-Please join the [caffe-users group](!forum/caffe-users) or [gitter chat]( to ask questions and talk about methods and models.
-Framework development discussions and thorough bug reports are collected on [Issues](
+Fix the issues:
-Happy brewing!
+* Compatible with Arm Compute Library version 17.06
+* When OpenCL initialization fails, even if Caffe uses CPU-mode,it doesn't work properly.
-## License and Citation
+### Version 0.1.0 - Jun 2, 2017
+ Initial version supports 10 Layers accelerated by Arm Compute Library version 17.05 :
-Caffe is released under the [BSD 2-Clause license](
-The BVLC reference models are released for unrestricted use.
+* Convolution Layer
+* Pooling Layer
+* LRN Layer
+* ReLU Layer
+* Sigmoid Layer
+* Softmax Layer
+* TanH Layer
+* AbsVal Layer
+* BNLL Layer
+* InnerProduct Layer
-Please cite Caffe in your publications if it helps your research:
+# 3 Issue Report
+Encounter any issue, please report on [issue report]( Issue report should contain the following information :
- @article{jia2014caffe,
- Author = {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor},
- Journal = {arXiv preprint arXiv:1408.5093},
- Title = {Caffe: Convolutional Architecture for Fast Feature Embedding},
- Year = {2014}
- }
+* 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