OSSInnovation
/
mindspore
1
0
Fork 26
Code Issues Pull Requests 7 Releases Wiki Activity

!6856 [MS][LITE]Modified the download link 

Merge pull request !6856 from gongdaguo/r1.0_modify_d_l
This commit is contained in:
mindspore-ci-bot 2020-09-25 15:43:38 +08:00 committed by Gitee
parent 28cb04a856 4d19aaa72e
commit 7f6800bc2c
7 changed files with 47 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mindspore/lite/test/models_onnx.cfg
View File

@ -1,4 +1,4 @@
mtk_detect-mbv2-shortcut-400-400-simplified.onnx
mtk_emotions-d2012-75.8%.onnx
mtk_face_features_v3.onnx
#mtk_face_features_v3.onnx
ml_face_3d.onnx

16
model_zoo/official/lite/image_classification/README.en.md
View File

@ -78,7 +78,13 @@ app
### Configuring MindSpore Lite Dependencies
When MindSpore C++ APIs are called at the Android JNI layer, related library files are required. You can use MindSpore Lite [source code compilation](https://www.mindspore.cn/tutorial/lite/en/master/use/build.html) to generate the MindSpore Lite version.　
When MindSpore C++ APIs are called at the Android JNI layer, related library files are required. You can use MindSpore Lite [source code compilation](https://www.mindspore.cn/tutorial/lite/en/master/use/build.html) to generate the MindSpore Lite version. In this case, you need to use the compile command of generate with image preprocessing module.
In this example, the build process automatically downloads the `mindspore-lite-1.0.0-minddata-arm64-cpu` by the `app/download.gradle` file and saves in the `app/src/main/cpp` directory.
Note: if the automatic download fails, please manually download the relevant library files and put them in the corresponding location.
mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz [Download link](https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.0/lite/android_aarch64/mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz)
```
android{
@ -126,15 +132,9 @@ target_link_libraries(
)
```
* In this example, the download.gradle File configuration auto download MindSpore Lite version, placed in the 'app/src/main/cpp/' directory.
Note: if the automatic download fails, please manually download the relevant library files and put them in the corresponding location.
mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz [Download link](https://download.mindspore.cn/model_zoo/official/lite/lib/mindspore%20version%201.0/mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz)
### Downloading and Deploying a Model File
In this example, the download.gradle File configuration auto download `mobilenetv2.ms `and placed in the 'app / libs / arm64-v8a' directory.
In this example, the download.gradle File configuration auto download `mobilenetv2.ms `and placed in the 'app/libs/arm64-v8a' directory.
Note: if the automatic download fails, please manually download the relevant library files and put them in the corresponding location.

15
model_zoo/official/lite/image_classification/README.md
View File

@ -86,14 +86,21 @@ app
### 配置MindSpore Lite依赖项
Android JNI层调用MindSpore C++ API时，需要相关库文件支持。可通过MindSpore Lite[源码编译](https://www.mindspore.cn/tutorial/lite/zh-CN/master/use/build.html)生成"mindspore-lite-X.X.X-mindata-armXX-cpu"库文件包（包含`libmindspore-lite.so`库文件和相关头文件，可包含多个兼容架构）。
Android JNI层调用MindSpore C++ API时，需要相关库文件支持。可通过MindSpore Lite[源码编译](https://www.mindspore.cn/tutorial/lite/zh-CN/master/use/build.html)生成`mindspore-lite-{version}-minddata-{os}-{device}.tar.gz`库文件包并解压缩（包含`libmindspore-lite.so`库文件和相关头文件），在本例中需使用生成带图像预处理模块的编译命令。
本示例中，build过程由download.gradle文件自动从华为服务器下载MindSpore Lite 版本文件，并放置在`app / src / main/cpp/`目录下。
> version：输出件版本号，与所编译的分支代码对应的版本一致。
>
> device：当前分为cpu（内置CPU算子）和gpu（内置CPU和GPU算子）。
>
> os：输出件应部署的操作系统。
* 注：若自动下载失败，请手动下载相关库文件并将其放在对应位置：
本示例中，build过程由download.gradle文件自动下载MindSpore Lite 版本文件，并放置在`app/src/main/cpp/`目录下。
mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz [下载链接](https://download.mindspore.cn/model_zoo/official/lite/lib/mindspore%20version%201.0/mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz)
* 注：若自动下载失败，请手动下载相关库文件，解压并放在对应位置：
mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz [下载链接](https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.0/lite/android_aarch64/mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz)
在app的`build.gradle`文件中配置CMake编译支持，以及`arm64-v8a`的编译支持，如下所示：
```
android{

2
model_zoo/official/lite/image_classification/app/download.gradle
View File

@ -10,7 +10,7 @@ def targetModelFile = "src/main/assets/model/mobilenetv2.ms"
def mindSporeLibrary_arm64 = "src/main/cpp/${mindsporeLite_Version}.tar.gz"
def modelDownloadUrl = "https://download.mindspore.cn/model_zoo/official/lite/mobilenetv2_openimage_lite/mobilenetv2.ms"
def mindsporeLiteDownloadUrl = "https://download.mindspore.cn/model_zoo/official/lite/lib/mindspore%20version%201.0/${mindsporeLite_Version}.tar.gz"
def mindsporeLiteDownloadUrl = "https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.0/lite/android_aarch64/${mindsporeLite_Version}.tar.gz"
def cleantargetMindSporeInclude = "src/main/cpp"

21
model_zoo/official/lite/object_detection/README.en.md
View File

@ -43,7 +43,14 @@ This object detection sample program on the Android device includes a Java layer
### Configuring MindSpore Lite Dependencies
In Android studio, the compiled mindpool-lite-x.x.x-mindata-armxx-cpu package (including ` libmindspot- lite.so `The library file and related header files, which can contain multiple compatible architectures), are unzipped and placed in the 'app / SRC / main / CPP' directory of the app project, and the` build.gradle `Cmake and 'arm64-v8a' and 'armeabi-v7a' are configured in the file as follows It is shown as follows:
When MindSpore C++ APIs are called at the Android JNI layer, related library files are required. You can use MindSpore Lite [source code compilation](https://www.mindspore.cn/tutorial/lite/en/master/use/build.html) to generate the MindSpore Lite version. In this case, you need to use the compile command of generate with image preprocessing module.
In this example, the build process automatically downloads the `mindspore-lite-1.0.0-minddata-arm64-cpu` by the `app/download.gradle` file and saves in the `app/src/main/cpp` directory.
Note: if the automatic download fails, please manually download the relevant library files and put them in the corresponding location.
mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz [Download link](https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.0/lite/android_aarch64/mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz)
```
android{
defaultConfig{
@ -54,7 +61,7 @@ android{
}
ndk{
abiFilters'armeabi-v7a', 'arm64-v8a'
abiFilters 'arm64-v8a'
}
}
}
@ -82,16 +89,6 @@ target_link_libraries(
)
```
In this example, the download.gradle File configuration auto download library file, placed in the 'app / libs / arm64-v8a' directory.
Note: if the automatic download fails, please manually download the relevant library files and put them in the corresponding location.
mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz [Download link](https://download.mindspore.cn/model_zoo/official/lite/lib/mindspore%20version%201.0/mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz)
### Downloading and Deploying a Model File
In this example, the download.gradle File configuration auto download `ssd.ms `and placed in the 'app / libs / arm64-v8a' directory.

26
model_zoo/official/lite/object_detection/README.md
View File

@ -85,9 +85,22 @@ app
### 配置MindSpore Lite依赖项
Android JNI层调用MindSpore C++ API时，需要相关库文件支持。可通过MindSpore Lite[源码编译](https://www.mindspore.cn/tutorial/lite/zh-CN/master/use/build.html)生成"mindspore-lite-X.X.X-mindata-armXX-cpu"库文件包（包含`libmindspore-lite.so`库文件和相关头文件，可包含多个兼容架构）。
Android JNI层调用MindSpore C++ API时，需要相关库文件支持。可通过MindSpore Lite[源码编译](https://www.mindspore.cn/tutorial/lite/zh-CN/master/use/build.html)生成`mindspore-lite-{version}-minddata-{os}-{device}.tar.gz`库文件包并解压缩（包含`libmindspore-lite.so`库文件和相关头文件），在本例中需使用生成带图像预处理模块的编译命令。
> version：输出件版本号，与所编译的分支代码对应的版本一致。
>
> device：当前分为cpu（内置CPU算子）和gpu（内置CPU和GPU算子）。
>
> os：输出件应部署的操作系统。
本示例中，build过程由download.gradle文件自动下载MindSpore Lite 版本文件，并放置在`app/src/main/cpp/`目录下。
* 注：若自动下载失败，请手动下载相关库文件，解压并放在对应位置：
mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz [下载链接](https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.0/lite/android_aarch64/mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz)
在app的`build.gradle`文件中配置CMake编译支持，以及`arm64-v8a`的编译支持，如下所示：
在Android Studio中将编译完成的mindspore-lite-X.X.X-mindata-armXX-cpu压缩包，解压之后放置在APP工程的`app/src/main/cpp`目录下，并在app的`build.gradle`文件中配置CMake编译支持，以及`arm64-v8a`和`armeabi-v7a`的编译支持，如下所示：
```
android{
defaultConfig{
@ -126,16 +139,9 @@ target_link_libraries(
)
```
本示例中，app build过程由download.gradle文件自动从华为服务器下载mindspore所编译的库及相关头文件，并放置在`src/main/cpp`工程目录下。
* 注：若自动下载失败，请手动下载相关库文件并将其放在对应位置：
* mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz [下载链接](https://download.mindspore.cn/model_zoo/official/lite/lib/mindspore%20version%201.0/mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz)
### 下载及部署模型文件
从MindSpore Model Hub中下载模型文件，本示例程序中使用的目标检测模型文件为`ssd.ms`，同样通过download.gradle脚本在APP构建时自动下载，并放置在`app/src/main/assets`工程目录下。
从MindSpore Model Hub中下载模型文件，本示例程序中使用的目标检测模型文件为`ssd.ms`，同样通过`download.gradle`脚本在APP构建时自动下载，并放置在`app/src/main/assets`工程目录下。
* 注：若下载失败请手动下载模型文件，ssd.ms [下载链接](https://download.mindspore.cn/model_zoo/official/lite/ssd_mobilenetv2_lite/ssd.ms)。

2
model_zoo/official/lite/object_detection/app/download.gradle
View File

@ -10,7 +10,7 @@ def targetModelFile = "src/main/assets/model/ssd.ms"
def mindSporeLibrary_arm64 = "src/main/cpp/${mindsporeLite_Version}.tar.gz"
def modelDownloadUrl = "https://download.mindspore.cn/model_zoo/official/lite/ssd_mobilenetv2_lite/ssd.ms"
def mindsporeLiteDownloadUrl = "https://download.mindspore.cn/model_zoo/official/lite/lib/mindspore%20version%201.0/${mindsporeLite_Version}.tar.gz"
def mindsporeLiteDownloadUrl = "https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.0/lite/android_aarch64/${mindsporeLite_Version}.tar.gz"
def cleantargetMindSporeInclude = "src/main/cpp"