Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
Xiaomi
Mace
提交
47894517
Mace
项目概览
Xiaomi
/
Mace
通知
106
Star
40
Fork
27
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
DevOps
流水线
流水线任务
计划
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
Mace
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
DevOps
DevOps
流水线
流水线任务
计划
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
流水线任务
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
47894517
编写于
6月 26, 2018
作者:
L
Liangliang He
浏览文件
操作
浏览文件
下载
差异文件
Merge branch 'update_docs' into 'master'
Update docs See merge request !606
上级
1977fe42
cb41250e
变更
6
隐藏空白更改
内联
并排
Showing
6 changed file
with
25 addition
and
25 deletion
+25
-25
README.md
README.md
+6
-6
README_zh.md
README_zh.md
+5
-5
docs/conf.py
docs/conf.py
+1
-1
docs/getting_started/how_to_build.rst
docs/getting_started/how_to_build.rst
+6
-6
docs/getting_started/introduction.rst
docs/getting_started/introduction.rst
+4
-4
docs/index.rst
docs/index.rst
+3
-3
未找到文件。
README.md
浏览文件 @
47894517
# M
i
AI Compute Engine
# M
obile
AI Compute Engine
[
![License
](
https://img.shields.io/badge/License-Apache%202.0-blue.svg
)
](LICENSE)
[
![License
](
https://img.shields.io/badge/License-Apache%202.0-blue.svg
)
](LICENSE)
[
![build status
](
http://v9.git.n.xiaomi.com/deep-computing/mace/badges/master/build.svg
)
](http://v9.git.n.xiaomi.com/deep-computing/mace/pipelines)
[
![build status
](
http://v9.git.n.xiaomi.com/deep-computing/mace/badges/master/build.svg
)
](http://v9.git.n.xiaomi.com/deep-computing/mace/pipelines)
[
Documentation
](
docs
)
|
[
Documentation
](
docs
)
|
[
FAQ
](
docs/faq.md
)
|
[
FAQ
](
docs/faq.md
)
|
[
Release Notes
](
RELEASE.md
)
|
[
Release Notes
](
RELEASE.md
)
|
[
M
iAI Model Zoo
](
http://v9.git.n.xiaomi.com/deep-computing
/mace-models
)
|
[
M
ACE Model Zoo
](
https://github.com/XiaoMi
/mace-models
)
|
[
Demo
](
mace/android
)
|
[
Demo
](
mace/
examples/
android
)
|
[
中文
](
README_zh.md
)
[
中文
](
README_zh.md
)
**M
i
AI Compute Engine**
(or
**MACE**
for short) is a deep learning inference framework optimized for
**M
obile
AI Compute Engine**
(or
**MACE**
for short) is a deep learning inference framework optimized for
mobile heterogeneous computing platforms. The design is focused on the following
mobile heterogeneous computing platforms. The design is focused on the following
targets:
targets:
*
Performance
*
Performance
...
@@ -43,7 +43,7 @@ targets:
...
@@ -43,7 +43,7 @@ targets:
*
[
Create a model deployment file
](
docs/getting_started/create_a_model_deployment.rst
)
*
[
Create a model deployment file
](
docs/getting_started/create_a_model_deployment.rst
)
## Performance
## Performance
[
M
iAI Compute Engine Model Zoo
](
http://v9.git.n.xiaomi.com/deep-computing
/mace-models
)
contains
[
M
ACE Model Zoo
](
https://github.com/XiaoMi
/mace-models
)
contains
several common neural networks models and built daily against a list of mobile
several common neural networks models and built daily against a list of mobile
phones. The benchmark result can be found in the CI result page.
phones. The benchmark result can be found in the CI result page.
...
@@ -63,7 +63,7 @@ please refer to [the contribution guide](docs/development/contributing.md).
...
@@ -63,7 +63,7 @@ please refer to [the contribution guide](docs/development/contributing.md).
[
Apache License 2.0
](
LICENSE
)
.
[
Apache License 2.0
](
LICENSE
)
.
## Acknowledgement
## Acknowledgement
M
iAI Compute Engine
depends on several open source projects located in
M
ACE
depends on several open source projects located in
[
third_party
](
third_party
)
directory. Particularly, we learned a lot from
[
third_party
](
third_party
)
directory. Particularly, we learned a lot from
the following projects during the development:
the following projects during the development:
*
[
Qualcomm Hexagon NN Offload Framework
](
https://source.codeaurora.org/quic/hexagon_nn/nnlib
)
: the Hexagon DSP runtime
*
[
Qualcomm Hexagon NN Offload Framework
](
https://source.codeaurora.org/quic/hexagon_nn/nnlib
)
: the Hexagon DSP runtime
...
...
README_zh.md
浏览文件 @
47894517
# M
iAI
计算引擎
# M
ACE - 移动人工智能
计算引擎
[
![License
](
https://img.shields.io/badge/License-Apache%202.0-blue.svg
)
](LICENSE)
[
![License
](
https://img.shields.io/badge/License-Apache%202.0-blue.svg
)
](LICENSE)
[
![build status
](
http://v9.git.n.xiaomi.com/deep-computing/mace/badges/master/build.svg
)
](http://v9.git.n.xiaomi.com/deep-computing/mace/pipelines)
[
![build status
](
http://v9.git.n.xiaomi.com/deep-computing/mace/badges/master/build.svg
)
](http://v9.git.n.xiaomi.com/deep-computing/mace/pipelines)
[
文档
](
docs
)
|
[
文档
](
docs
)
|
[
FAQ
](
docs/faq.md
)
|
[
FAQ
](
docs/faq.md
)
|
[
发布记录
](
RELEASE.md
)
|
[
发布记录
](
RELEASE.md
)
|
[
M
iAI Model Zoo
](
http://v9.git.n.xiaomi.com/deep-computing
/mace-models
)
|
[
M
ACE Model Zoo
](
https://github.com/XiaoMi
/mace-models
)
|
[
Demo
](
mace/android
)
|
[
Demo
](
mace/
examples/
android
)
|
[
English
](
README.md
)
[
English
](
README.md
)
**M
iAI Compute Engine
**
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。
**M
obile 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。
主要从以下的角度做了专门的优化:
主要从以下的角度做了专门的优化:
*
性能
*
性能
*
代码经过NEON指令,OpenCL以及Hexagon HVX专门优化,并且采用
*
代码经过NEON指令,OpenCL以及Hexagon HVX专门优化,并且采用
...
@@ -35,7 +35,7 @@
...
@@ -35,7 +35,7 @@
*
[
如何构建
](
docs/getting_started/how_to_build.rst
)
*
[
如何构建
](
docs/getting_started/how_to_build.rst
)
## 性能评测
## 性能评测
[
M
iAI Model Zoo
](
http://v9.git.n.xiaomi.com/deep-computing
/mace-models
)
[
M
ACE Model Zoo
](
https://github.com/XiaoMi
/mace-models
)
包含若干常用模型,并且会对一组手机进行每日构建。最新的性能评测结果可以从项目的持续集成页面获取。
包含若干常用模型,并且会对一组手机进行每日构建。最新的性能评测结果可以从项目的持续集成页面获取。
## 交流与反馈
## 交流与反馈
...
...
docs/conf.py
浏览文件 @
47894517
...
@@ -6,7 +6,7 @@
...
@@ -6,7 +6,7 @@
import
recommonmark.parser
import
recommonmark.parser
import
sphinx_rtd_theme
import
sphinx_rtd_theme
project
=
u
'M
iAI Compute Engine
'
project
=
u
'M
obile AI Compute Engine (MACE)
'
author
=
u
'%s Developers'
%
project
author
=
u
'%s Developers'
%
project
copyright
=
u
'2018, %s'
%
author
copyright
=
u
'2018, %s'
%
author
...
...
docs/getting_started/how_to_build.rst
浏览文件 @
47894517
...
@@ -19,7 +19,7 @@ Supported Platforms
...
@@ -19,7 +19,7 @@ Supported Platforms
Environment
Requirement
Environment
Requirement
-------------------------
-------------------------
M
iAI
Compute
Engine
requires
the
following
dependencies
:
M
ACE
requires
the
following
dependencies
:
..
list
-
table
::
..
list
-
table
::
:
widths
:
auto
:
widths
:
auto
...
@@ -67,7 +67,7 @@ MiAI Compute Engine requires the following dependencies:
...
@@ -67,7 +67,7 @@ MiAI Compute Engine requires the following dependencies:
``
export
ANDROID_NDK_HOME
=/
path
/
to
/
ndk
``
to
specify
ANDROID_NDK_HOME
``
export
ANDROID_NDK_HOME
=/
path
/
to
/
ndk
``
to
specify
ANDROID_NDK_HOME
M
iAI
Compute
Engine
provides
Dockerfile
with
these
dependencies
installed
,
M
ACE
provides
Dockerfile
with
these
dependencies
installed
,
you
can
build
the
image
from
the
Dockerfile
,
you
can
build
the
image
from
the
Dockerfile
,
..
code
::
sh
..
code
::
sh
...
@@ -95,7 +95,7 @@ Usage
...
@@ -95,7 +95,7 @@ Usage
--------
--------
=======================================
=======================================
1.
Pull
M
iAI
Compute
Engine
source
code
1.
Pull
M
ACE
source
code
=======================================
=======================================
..
code
::
sh
..
code
::
sh
...
@@ -166,7 +166,7 @@ optimizations for different runtimes,
...
@@ -166,7 +166,7 @@ optimizations for different runtimes,
-
Caffe
-
Caffe
M
iAI
Compute
Engine
converter
only
supports
Caffe
1.0
+,
you
need
to
upgrade
M
ACE
converter
only
supports
Caffe
1.0
+,
you
need
to
upgrade
your
models
with
Caffe
built
-
in
tool
when
necessary
,
your
models
with
Caffe
built
-
in
tool
when
necessary
,
..
code
::
bash
..
code
::
bash
...
@@ -184,7 +184,7 @@ your models with Caffe built-in tool when necessary,
...
@@ -184,7 +184,7 @@ your models with Caffe built-in tool when necessary,
-----------------
-----------------
3.1
Overview
3.1
Overview
-----------------
-----------------
M
iAI
Compute
Engine
can
build
either
static
or
shared
library
(
which
is
M
ACE
can
build
either
static
or
shared
library
(
which
is
specified
by
``
linkshared
``
in
YAML
model
deployment
file
).
specified
by
``
linkshared
``
in
YAML
model
deployment
file
).
The
followings
are
two
use
cases
.
The
followings
are
two
use
cases
.
...
@@ -208,7 +208,7 @@ The followings are two use cases.
...
@@ -208,7 +208,7 @@ The followings are two use cases.
There
will
be
around
of
1
~
10
%
performance
drop
for
GPU
There
will
be
around
of
1
~
10
%
performance
drop
for
GPU
runtime
compared
to
the
well
tuned
library
.
runtime
compared
to
the
well
tuned
library
.
M
iAI
Compute
Engine
provide
command
line
tool
(``
tools
/
converter
.
py
``)
for
M
ACE
provide
command
line
tool
(``
tools
/
converter
.
py
``)
for
model
conversion
,
compiling
,
test
run
,
benchmark
and
correctness
validation
.
model
conversion
,
compiling
,
test
run
,
benchmark
and
correctness
validation
.
..
note
::
..
note
::
...
...
docs/getting_started/introduction.rst
浏览文件 @
47894517
Introduction
Introduction
============
============
M
iAI
Compute
Engine
is
a
deep
learning
inference
framework
optimized
for
M
obile
AI
Compute
Engine
(
MACE
)
is
a
deep
learning
inference
framework
optimized
for
mobile
heterogeneous
computing
platforms
.
The
following
figure
shows
the
mobile
heterogeneous
computing
platforms
.
The
following
figure
shows
the
overall
architecture
.
overall
architecture
.
...
@@ -12,8 +12,8 @@ overall architecture.
...
@@ -12,8 +12,8 @@ overall architecture.
Model
format
Model
format
------------
------------
M
iAI
Compute
Engine
defines
a
customized
model
format
which
is
similar
to
M
ACE
defines
a
customized
model
format
which
is
similar
to
Caffe2
.
The
M
iAI
model
can
be
converted
from
exported
models
by
TensorFlow
Caffe2
.
The
M
ACE
model
can
be
converted
from
exported
models
by
TensorFlow
and
Caffe
.
A
YAML
file
is
used
to
describe
the
model
deployment
details
.
In
the
and
Caffe
.
A
YAML
file
is
used
to
describe
the
model
deployment
details
.
In
the
next
chapter
,
there
is
a
detailed
guide
showing
how
to
create
this
YAML
file
.
next
chapter
,
there
is
a
detailed
guide
showing
how
to
create
this
YAML
file
.
...
@@ -26,7 +26,7 @@ more frameworks will be supported in the future.
...
@@ -26,7 +26,7 @@ more frameworks will be supported in the future.
Model
loading
Model
loading
-------------
-------------
The
M
iAI
model
format
contains
two
parts
:
the
model
graph
definition
and
The
M
ACE
model
format
contains
two
parts
:
the
model
graph
definition
and
the
model
parameter
tensors
.
The
graph
part
utilizes
Protocol
Buffers
the
model
parameter
tensors
.
The
graph
part
utilizes
Protocol
Buffers
for
serialization
.
All
the
model
parameter
tensors
are
concatenated
for
serialization
.
All
the
model
parameter
tensors
are
concatenated
together
into
a
continuous
byte
array
,
and
we
call
this
array
tensor
data
in
together
into
a
continuous
byte
array
,
and
we
call
this
array
tensor
data
in
...
...
docs/index.rst
浏览文件 @
47894517
M
i
AI Compute Engine Documentation
M
obile
AI Compute Engine Documentation
=================================
=================================
=====
Welcome to M
i
AI Compute Engine documentation.
Welcome to M
obile
AI Compute Engine documentation.
The main documentation is organized into the following sections:
The main documentation is organized into the following sections:
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录