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
6aa007f4
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
6aa007f4
编写于
7月 03, 2018
作者:
L
liutuo
提交者:
liuqi
7月 09, 2018
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
update basic usage doc
上级
cfd3bbab
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
15 addition
and
14 deletion
+15
-14
docs/user_guide/basic_usage.rst
docs/user_guide/basic_usage.rst
+15
-14
未找到文件。
docs/user_guide/basic_usage.rst
浏览文件 @
6aa007f4
...
...
@@ -5,7 +5,7 @@ Basic usage
Build
and
run
an
example
model
--------------------------------
Make
sure
the
environment
has
been
set
up
correctly
already
.(
refer
to
`
installation
`)
Make
sure
the
environment
has
been
set
up
correctly
already
(
refer
to
`
Installation
`).
Pull
the
mace
model
zoo
project
.
...
...
@@ -14,7 +14,7 @@ Pull the mace model zoo project.
git
clone
https
://
github
.
com
/
XiaoMi
/
mace
-
models
.
git
Here
we
use
the
provided
mobilenet
-
v2
model
in
mace
model
zoo
as
an
example
.
Plug
an
android
phone
into
your
pc
and
enable
Developer
Mode
of
the
phon
e
.
Plug
an
android
device
into
your
pc
and
enable
Developer
Mode
for
the
devic
e
.
..
code
::
sh
...
...
@@ -32,7 +32,7 @@ Validate and benchmark the model.
..
note
::
1.
If
you
want
to
build
and
run
the
model
on
pc
,
just
use
the
mobilenet
-
v2
-
host
.
yml
file
instead
.
If
you
want
to
build
and
run
the
model
on
pc
,
just
use
the
mobilenet
-
v2
-
host
.
yml
file
instead
for
``--
config
``
.
Build
your
own
model
...
...
@@ -48,11 +48,11 @@ Mace now supports models from tensorflow and caffe.
Prepare
your
tensorflow
model
.
pb
file
.
Use
`
Graph
Transform
Tool
<
https
://
github
.
com
/
tensorflow
/
tensorflow
/
blob
/
master
/
tensorflow
/
tools
/
graph_transforms
/
README
.
md
>`
__
to
optimize
you
model
for
inference
.
to
optimize
you
r
model
for
inference
.
This
tool
will
improve
the
efficiency
of
inference
by
making
several
optimizations
like
operations
folding
,
redundant
node
removal
etc
.
We
strongly
recommend
to
use
it
before
building
.
folding
,
redundant
node
removal
etc
.
We
strongly
recommend
MACE
users
to
use
it
before
building
.
The
following
command
shows
how
to
use
it
for
CPU
/
GPU
,
The
following
command
shows
how
to
use
the
graph
transform
tool
for
CPU
/
GPU
,
..
code
::
bash
...
...
@@ -75,7 +75,7 @@ Mace now supports models from tensorflow and caffe.
-
Caffe
MACE
converter
only
supports
Caffe
1.0
+,
you
need
to
upgrade
your
model
s
with
Caffe
built
-
in
tool
if
necessary
,
your
model
by
using
the
Caffe
built
-
in
tool
if
your
model
is
from
lower
version
caffe
.
..
code
::
bash
...
...
@@ -102,7 +102,7 @@ Modify one of them for your own case.
..
literalinclude
::
models
/
demo_app_models_caffe
.
yml
:
language
:
yaml
More
details
about
model
deployment
file
,
refer
to
`
a
dvanced_usage
`.
More
details
about
model
deployment
file
,
refer
to
`
A
dvanced_usage
`.
======================================
...
...
@@ -110,9 +110,9 @@ More details about model deployment file, refer to `advanced_usage`.
======================================
MACE
provides
a
python
tool
(``
tools
/
converter
.
py
``)
for
model
conversion
,
compiling
,
test
run
,
benchmark
and
correctness
validation
.
model
conversion
,
compiling
,
test
ing
,
benchmark
and
validation
.
MACE
can
build
either
static
or
shared
li
nk
li
brary
(
which
is
MACE
can
build
either
static
or
shared
library
(
which
is
specified
by
``
linkshared
``
in
YAML
model
deployment
file
).
**
Commands
**
...
...
@@ -151,8 +151,8 @@ specified by ``linkshared`` in YAML model deployment file).
..
warning
::
1.
Plug
an
android
phon
e
into
your
pc
and
enable
Developer
Mode
before
building
.
2.
Please
``
build
``
your
model
before
``
run
``
or
``
benchmark
``
it
.
1.
Plug
an
android
devic
e
into
your
pc
and
enable
Developer
Mode
before
building
.
2.
If
you
want
to
build
the
model
for
pc
,
set
``
target_abis
:
[
host
]``
and
``
runtime
:
cpu
``
in
your
deployment
YAML
file
.
============================================
...
...
@@ -160,10 +160,10 @@ specified by ``linkshared`` in YAML model deployment file).
============================================
``
build
``
command
will
generate
the
static
/
shared
library
,
model
files
and
header
files
.
All
of
these
files
have
been
packaged
into
header
files
.
All
of
these
generated
files
will
be
packaged
into
``
path
/
to
/
mace
/
build
/${
library_name
}/
libmace_
${
library_name
}.
tar
.
gz
``.
``${
library_name
}``
is
the
name
you
defined
in
the
first
line
of
your
de
mployment
yaml
file
.
``${
library_name
}``
is
the
name
you
defined
in
the
first
line
of
your
de
ployment
YAML
file
.
-
The
generated
``
static
``
library
files
are
organized
as
follows
,
...
...
@@ -233,6 +233,7 @@ header files. All of these files have been packaged into
Unpack
the
generated
libmace_
${
library_name
}.
tar
.
gz
file
and
copy
all
of
the
uncompressed
files
into
your
project
.
Please
refer
to
\
``
mace
/
examples
/
example
.
cc
``\
for
full
usage
.
The
following
lists
the
key
steps
.
..
code
::
cpp
...
...
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