GithubHelp home page GithubHelp logo

yeyupiaoling / classificationforandroid Goto Github PK

View Code? Open in Web Editor NEW
154.0 4.0 67.0 45.13 MB

在Android使用深度学习模型实现图像识别,本项目提供了多种使用方式,使用到的框架如下:Tensorflow Lite、Paddle Lite、MNN、TNN

License: Apache License 2.0

Java 46.14% CMake 0.81% C++ 49.39% C 3.66%
paddlepaddle tensorflow2 mnn tnn deep-learning classification

classificationforandroid's Issues

求个交流群

Android开发,求个交流群。或者一起学习研究MNN

TNN模块内存异常

TNN demo我们监控发现,内存会异常,物理内存使用率会越来越大,知道占满异常退出

报错:I/HwViewRootImpl: removeInvalidNode all the node in jank list is out of time。

在使用TNN图像分类的项目时,我改用了自己的inception-v2-9.opt.tnnmodel,这个与项目中的原模型的输入shape是一样的,也是基于ImageNet得到的有1000类的模型,但是Log中输出了以上问题,不知该如何解决。上述问题出现在“选择照片”部分,无论在相册中选择什么图片,最终显示的推理结果都是“麦克风”,如下所示:
image
image
image

如果需要更详细的信息,

java.lang.UnsatisfiedLinkError: dlopen failed: library "libMNN.so" not found

hi,I ran your code in Android Studio,do what you say in README,
I build mnn .so files, and put them in src/main/jniLibs/, total two folder arm64-8v and armeabi-v7a.
but I got this error ,
image

my compute's info:

  • windows 10
  • i5- 7300

image

I run code in an android Virtual Devices:
image

I run a Virtual Device with CPU/ABI is arm64-8v or armeabi-v7a, it show

Error while waiting for device: The emulator process for AVD Pixel_4_API_30_arm64 was killed.

I try some other method to solve this, but failed, could you help me?

关于图像的均值和标准差

您好,非常感谢您提供的教程!
我看到关于设置图像均值和标准差的代码十分重要,我只接触过mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]这样的处理,这应该是适应imagenet预训练模型时大家通常采用的,看起来跟您的代码里的数字差别很大,请问您能告诉我您的代码里的图像均值和标准差是如何确定的吗?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.