Что такое mace cl compiled program bin
Перейти к содержимому

Что такое mace cl compiled program bin

  • автор:

MIUI 12 выведет безопасность пользовательских данных на новый уровень

Xiaomi разработала программную платформу под названием MACE (Mobile AI Compute Engine), которая выведет безопасность пользовательских данных на новый уровень. Дебютирует MACE в прошивке MIUI 12, которую должны представить уже очень скоро – 27 апреля.

MIUI 12 выведет безопасность пользовательских данных на новый уровень

Само главное достоинство MACE – автономность. Она выполняет все процессы прямо на мобильном устройстве, а не использует для обработки мощности серверов облачных сервисов. Ну а коль скоро данные никуда не отправляются, то и перехватить их невозможно. Но это еще не все – в MIUI 12 появится механизм защиты информации под названием «отличительная конфиденциальность». Его смысл состоит в добавлении к передаваемым посредством беспроводной связи пользовательским данным небольшой части фальшивого кода – безвредного, но в то же время мешающего декодированию информации в случае перехвата.

Алгоритм «отличительной конфиденциальности» в сочетании с MACE должны сделать смартфоны с MIUI 12 более защищенными. Для всех нынешних пользователей смартфонов Xiaomi прелесть состоит в том, что эти системы защиты реализованы программно, так что пользователи моделей, которым обещано обновление до MIUI 12, получат новые системы защиты автоматически с новой прошивкой.

Что такое mace cl compiled program bin

Jgb49 no está en línea

Jgb49

Miembro del foro
Fecha de registro: feb 2018
Mensajes: 326
Modelo de smartphone: Xiaomi redmi note 9 pro
Tu operador: Simyo
Que es mace_cl_compiled_program.bin

Pues eso, que no deja de aparecer este archivo en mi note 9 pro y no se que es. Aparece en almacenamiento interno y tambi�n dentro de la carpeta Dcim, lo elimino y al poco vuelve a aparecer.

22/12/23, 09:40:28

rpla no está en línea

rpla

Usuario poco activo
Fecha de registro: abr 2012
Mensajes: 2
Tu operador: Movistar

Mace (Mobile AI Compute Engine) es el proyecto de desarrollo de Inteligencia Artificial m�s grande creado por Xiaomi para sus smartphones. Gracias al uso de nuevas programaciones y algoritmos Xiaomi asegura que la privacidad del usuario en MIUI 12 queda apartada de los servidores, siendo relegada a quedarse en el dispositivo del usuario.

El c�digo est� en Gitub

Saved searches

Use saved searches to filter your results more quickly

Cancel Create saved search

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

XiaoMi / mace Public

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

License

XiaoMi/mace

This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.

Go to file

Folders and files

Last commit message
Last commit date

Latest commit

History

View all files

Repository files navigation

Mobile AI Compute Engine (or MACE for short) is a deep learning inference framework optimized for mobile heterogeneous computing on Android, iOS, Linux and Windows devices. The design focuses on the following targets:

  • Performance
    • Runtime is optimized with NEON, OpenCL and Hexagon, and Winograd algorithm is introduced to speed up convolution operations. The initialization is also optimized to be faster.
    • Chip dependent power options like big.LITTLE scheduling, Adreno GPU hints are included as advanced APIs.
    • UI responsiveness guarantee is sometimes obligatory when running a model. Mechanism like automatically breaking OpenCL kernel into small units is introduced to allow better preemption for the UI rendering task.
    • Graph level memory allocation optimization and buffer reuse are supported. The core library tries to keep minimum external dependencies to keep the library footprint small.
    • Model protection has been the highest priority since the beginning of the design. Various techniques are introduced like converting models to C++ code and literal obfuscations.
    • Good coverage of recent Qualcomm, MediaTek, Pinecone and other ARM based chips. CPU runtime supports Android, iOS and Linux.
    • TensorFlow, Caffe and ONNX model formats are supported.

    Getting Started

    Performance

    MACE Model Zoo contains several common neural networks and models which will be built daily against a list of mobile phones. The benchmark results can be found in the CI result page (choose the latest passed pipeline, click release step and you will see the benchmark results). To get the comparison results with other frameworks, you can take a look at MobileAIBench project.

    Communication

    • GitHub issues: bug reports, usage issues, feature requests
    • Slack: mace-users.slack.com
    • QQ群: 756046893

    Contributing

    Any kind of contribution is welcome. For bug reports, feature requests, please just open an issue without any hesitation. For code contributions, it’s strongly suggested to open an issue for discussion first. For more details, please refer to the contribution guide.

    License

    Acknowledgement

    MACE depends on several open source projects located in the third_party directory. Particularly, we learned a lot from the following projects during the development:

    • Qualcomm Hexagon NN Offload Framework: the Hexagon DSP runtime depends on this library.
    • TensorFlow, Caffe, SNPE, ARM ComputeLibrary, ncnn, ONNX and many others: we learned many best practices from these projects.

    Finally, we also thank the Qualcomm, Pinecone and MediaTek engineering teams for their help.

    Saved searches

    Use saved searches to filter your results more quickly

    Cancel Create saved search

    You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

    XiaoMi / mace Public

    Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

    By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

    Already on GitHub? Sign in to your account

    How to link yml and android project?(如何链接yml和android项目?) #691

    chartores opened this issue Nov 5, 2020 · 14 comments

    How to link yml and android project?(如何链接yml和android项目?) #691

    chartores opened this issue Nov 5, 2020 · 14 comments

    Comments

    chartores commented Nov 5, 2020

    Hello.
    To use the current mace library, the settings and tests have been completed in basic PC and Android.

    Through the process below, I have a rough understanding of how and how to create an application using the mace library on Android.

    train.py -> xxx.meta / xxx.index / xxx.data -> gen_frozen_pb .py -> xxx.pb -> [Mace Library]converter.py -> xxx.yml

    However, even if I look at the’mace’ documentation, I don’t understand the process of how to do it when connecting yml and Android.

    I would really appreciate it if you could tell me how to do it in detail.

    train.py-> xxx.meta / xxx.index / xxx.data-> gen_frozen_pb .py-> xxx.pb-> [Mace库] converter.py-> xxx.yml

    The text was updated successfully, but these errors were encountered:

    chartores commented Nov 5, 2020

    感谢您详细解释。 理论部分是有意义的。 如果您看下面的过程,’*. *’ 我不了解链接这些部分的部分。

    train.py-> xxx.meta / xxx.index / xxx.data-> gen_frozen_pb .py-> xxx.pb->
    ->[Mace library] converter.py-> xxx.yml -> *. * -> xxx.so OR xxx.a -> jni -> 안드로이드(자바)

    这是一个基本的猜测,但这是一种用“ xxx.a OR xxx.so”替换“ yml(训练后的pb文件配置文件)”并将其放入Android项目的方法吗?

    Collaborator
    lu229 commented Nov 5, 2020

    @chartores Could you speak English? I can’t understand what you mean in Chinese.

    chartores commented Nov 6, 2020

    Ah, I thought I was a Chinese national, so I translated it in Chinese. It seems that there were a lot of errors in the automatic translation. If you would like to write a comment in English again, thank you for the detailed explanation. (Actually, I am not good at both Chinese and English.)

    Thanks to «lu229», little by little, we are looking for clues and solving them. Thank you.
    But I still don’t know if the android connection method in yml is the way I think it is.

    If you look below, this is the process I think.

    train.py-> xxx.meta / xxx.index / xxx.data->

    gen_frozen_pb .py-> xxx.pb->

    . -> xxx.so OR xxx.a -> jni -> Android (Java)

    Question 1: Considering the above process, it’s my personal guess, but do you replace «xxx.yml» with «xxx.a» or xxx.so file and put it in your Android project??

    Question 2: Do you replace «xxx.yml» with «xxx.a» or xxx.so file according to the document addressed in the previous comment?

    Question 3: I am wondering if it is correct to change the lower part of the contents of the CmakeLists.txt file in the macelibrary folder in the project.
    [set(mobilenet_lib $/src/main/cpp/model/arm64-v8a/mobilenet.a)]

    Actually, this process and method are very new and difficult, but thank you for your help every time.

    Collaborator
    lu229 commented Nov 6, 2020

    @chartores
    Perhaps you should read the document first.

    Question 1: Considering the above process, it’s my personal guess, but do you replace «xxx.yml» with «xxx.a» or xxx.so file and put it in your Android project??
    The above process (you thought) is not right, in MACE, we use converter.py to convert the model files(such as xxx.pb) to mace model file(or lib), the xxx.yml is a config file which is used to config the model’s info for the converter.py . after the convert, you can get the model file(or lib). please refer to this document.

    Question 2: Do you replace «xxx.yml» with «xxx.a» or xxx.so file according to the document addressed in the previous comment?
    No, please refer to this document and build the «xxx.a» or xxx.so file.

    Question 3: I am wondering if it is correct to change the lower part of the contents of the CmakeLists.txt file in the macelibrary folder in the project.
    [set(mobilenet_lib $/src/main/cpp/model/arm64-v8a/mobilenet.a)]

    yes, if you convert your model (in code mode) success and get the model lib(.a), then you can modify this part to replace the mobilenet.a with your own model lib.

    chartores commented Nov 6, 2020 •

    @lu229
    Wow. That’s amazing. Thank you very much.
    I never thought I would convert the deep learning model trained with «converter.py» to «xxx.yml» and «xxx.lib».
    Can I change the contents of the «CmakeLists.txt» file and upload the «xxx.yml» and «xxx.lib» files to the Android project?
    Maybe it’s right.
    Thank you very much. It was a great help.
    I hope you will try it today and next week and succeed.
    Have a happy day.

    Collaborator
    lu229 commented Nov 6, 2020

    @chartores
    you can convert the deep learning model trained with «converter.py» to «xxx.lib» but not «xxx.yml», «xxx.yml» is only a config file, please read the document first, or you can not try it successfully.

    chartores commented Nov 6, 2020

    @lu229
    I checked again. I was mistaken.
    «xxx.yml» -> «xxx.lib» is created.
    Thank you.
    I created an xxx.a file using converter.py and xxx.xml files.

    chartores commented Nov 6, 2020 •

    @lu229
    We proceeded as lu229 informed us, and then proceeded to the next process.
    There is already an xxx.a file (70MB) in the project in the link below.
    The newly created xxx.a file is (38MB).
    So, the old one was deleted and the new one was put in.
    (When creating the «xxx.a» file, I used the project’s «xxx.pb» file and «xxx.yml» file.)
    The test was completed by building in the previous project.
    (https://github.com/edvardHua/PoseEstimationForMobile/tree/master/android_demo/demo_mace)
    (https://github.com/edvardHua/PoseEstimationForMobile/tree/master/android_demo/demo_mace/macelibrary/src/main/cpp/lib/armeabi-v7a/cpm.a)

    However, when I tried to build in Android Studio by replacing the xxx.a file, the following error occurred.
    Question 1: Was the replacement method wrong? Or was it wrong to build in Android Studio?
    Q2: Should I build with ABD?
    Question 3: The size difference between the existing file and the new file is very different. What is the problem?
    (When you read the above project, it seems that mace 0.9 was used. The newly created file used the latest version of mace.)
    There are many difficulties.

    > Build command failed. > Error while executing process /home/peng_ai/android/cmake/3.6.4111459/bin/cmake with arguments > [1/1] Linking CXX shared library ../../../../build/intermediates/cmake/debug/obj/armeabi-v7a/libmace_mobile_jni.so > FAILED: : && /opt/android-ndk-r16b/toolchains/llvm/prebuilt/linux-x86_64/bin/clang++ --target=armv7-none-linux-androideabi --gcc-toolchain=/opt/android-ndk-r16b/toolchains/arm-linux-androideabi-4.9/prebuilt/linux-x86_64 --sysroot=/opt/android-ndk-r16b/sysroot -fPIC -isystem /opt/android-ndk-r16b/sysroot/usr/include/arm-linux-androideabi -D__ANDROID_API__=21 -g -DANDROID -ffunction-sections -funwind-tables -fstack-protector-strong -no-canonical-prefixes -march=armv7-a -mfloat-abi=softfp -mfpu=vfpv3-d16 -fno-integrated-as -mthumb -Wa,--noexecstack -Wformat -Werror=format-security -std=c++11 -fopenmp -O0 -fno-limit-debug-info -Wl,--exclude-libs,libgcc.a -Wl,--exclude-libs,libatomic.a --sysroot /opt/android-ndk-r16b/platforms/android-21/arch-arm -Wl,--build-id -Wl,--warn-shared-textrel -Wl,--fatal-warnings -Wl,--fix-cortex-a8 -Wl,--no-undefined -Wl,-z,noexecstack -Qunused-arguments -Wl,-z,relro -Wl,-z,now -shared -Wl,-soname,libmace_mobile_jni.so -o ../../../../build/intermediates/cmake/debug/obj/armeabi-v7a/libmace_mobile_jni.so CMakeFiles/mace_mobile_jni.dir/src/main/cpp/spe.cc.o ../../../../src/main/cpp/lib/armeabi-v7a/libmace.a ../../../../src/main/cpp/model/armeabi-v7a/cpm.a /opt/android-ndk-r16b/platforms/android-21/arch-arm/usr/lib/liblog.so -latomic -lm "/opt/android-ndk-r16b/sources/cxx-stl/gnu-libstdc++/4.9/libs/armeabi-v7a/libgnustl_static.a" && : > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::Argument* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::Argument* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::Argument* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::InputOutputInfo* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::InputOutputInfo* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/port/logger.h:51: error: undefined reference to 'mace::port::VLogLevelFromStr(char const*)' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/port/logger.h:45: error: undefined reference to 'mace::port::LogLevelFromStr(char const*)' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/port/env.h:66: error: undefined reference to 'mace::port::Env::Default()' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/utils/logging.h:103: error: undefined reference to 'mace::port::Logger::Logger(char const*, int, mace::LogLevel)' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/utils/logging.h:103: error: undefined reference to 'mace::port::Logger::~Logger()' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/utils/logging.h:103: error: undefined reference to 'mace::port::Logger::~Logger()' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::OperatorDef* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::OperatorDef* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::OperatorDef* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::OperatorDef* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::ConstTensor* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::ConstTensor* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::ConstTensor* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::ConstTensor* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/port/env.h:66: error: undefined reference to 'mace::port::Env::Default()' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/utils/logging.h:109: error: undefined reference to 'mace::port::Logger::Logger(char const*, int, mace::LogLevel)' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/utils/logging.h:109: error: undefined reference to 'mace::port::Logger::~Logger()' > bazel-out/armeabi-v7a-opt/bin/include/_virtual_includes/public_headers/mace/utils/logging.h:109: error: undefined reference to 'mace::port::Logger::~Logger()' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::Argument* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::OutputShape* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::OutputShape* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::OutputShape* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > external/com_google_protobuf/src/google/protobuf/repeated_field.h:643: error: undefined reference to 'mace::OutputShape* google::protobuf::Arena::CreateMaybeMessage(google::protobuf::Arena*)' > clang++: error: linker command failed with exit code 1 (use -v to see invocation) > ninja: build stopped: subcommand failed. 

Добавить комментарий

Ваш адрес email не будет опубликован. Обязательные поля помечены *