amitshekhariitbhu/androidtensorflowmachinelearningexample

Android TensorFlow MachineLearning Example (Building TensorFlow for Android)

About me

Hi, I am Amit Shekhar, I have taught and mentored many developers, and their efforts landed them high-paying tech jobs, helped many tech companies in solving their unique problems, and created many open-source libraries being used by top companies. I am passionate about sharing knowledge through open-source, blogs, and videos.

Learn from my blogs: amitshekhar.me/blog

Learn from my videos: youtube.com/@amitshekhar

Get High Paying Tech Job: amitshekhar.me

You can connect with me on:

• Twitter
• LinkedIn

androidtensorflowmachinelearningexample's Issues

我想使用自己训练的模型文件.pb文件（File）,请问如何操作？what can i do ?

plese tell me ,what can i do to use myself .pb File ??

Using Inception V3 instead of 5h?

The app crashes after a few seconds of startup when used Inception V3. The current one is 5h. I've set Image_Size=299, Image_Mean=128, inputname to "mul" and output name to "final_result".

i am trying to build .so file in the tensorflow workspace directory but i am unable to build the error that come is give below

How to use placeholder

I want to use tensorflow model in android.But I don't know how to use placeholder.Can you help me?

App crashes

The App crashes when I am trying to run it using my own graph file and labels file.
I tweaked the code in mainActivity.java accordingly.

Is the app hardcoded to run using only your graph and label files?

No operation named [ipnode] in the Graph

I have completed training the dataset using TensorFlow and I am freezing the model. A protobuffer file(.pb) has been created and I am providing the same to Android Studio.

After running the app I am getting the following error:"No operation named [ipnode] in the Graph".

TechStack:
Spyder(Python 3.7)
Tensorflow version-1.13.1
Android Studio version- 3.4
compile SDKVersion is 28 and TargetVersion is 28 in build.grade (Module:app)

.so file is not available

From the medium blog:
Now we have both jar and .so file. I have already built both .so file and jar, you can directly use from the below project.

I did not find the .so file.

The app is built, but nothing happens.

The app is built, but nothing happens.
No apps installed.

What's going on?

cant build .so file

I followed the steps to your blog but I get an error about c/c++ files in the cpp folder(created by itself). I dont know how you built the .so file. I have built the jar file fine.

Can I make a request

I need function like this:
I will enter a set of images and when I Detect Object some thing,
this program can match between some thing to images
is that possible?

run app is error

Process: com.mindorks.tensorflowexample, PID: 517
java.lang.RuntimeException: Error initializing TensorFlow!
at com.mindorks.tensorflowexample.MainActivity$5.run(MainActivity.java:158)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1113)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:588)
at java.lang.Thread.run(Thread.java:818)
Caused by: java.lang.RuntimeException: Native TF methods not found; check that the correct native libraries are present and loaded.
at org.tensorflow.contrib.android.TensorFlowInferenceInterface.(TensorFlowInferenceInterface.java:57)
at com.mindorks.tensorflowexample.TensorFlowImageClassifier.create(TensorFlowImageClassifier.java:108)
at com.mindorks.tensorflowexample.MainActivity$5.run(MainActivity.java:147)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1113) 
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:588) 
at java.lang.Thread.run(Thread.java:818) 

error creating so file

i have followed the procedure you described to create the so file.
i modified the workspace file and added the last 2 parts so thew workspace became as follows

workspace(name = "org_tensorflow")

http_archive(
name = "io_bazel_rules_closure",
sha256 = "a38539c5b5c358548e75b44141b4ab637bba7c4dc02b46b1f62a96d6433f56ae",
strip_prefix = "rules_closure-dbb96841cc0a5fb2664c37822803b06dab20c7d1",
urls = [
"https://mirror.bazel.build/github.com/bazelbuild/rules_closure/archive/dbb96841cc0a5fb2664c37822803b06dab20c7d1.tar.gz",
"https://github.com/bazelbuild/rules_closure/archive/dbb96841cc0a5fb2664c37822803b06dab20c7d1.tar.gz", # 2018-04-13
],
)

load("@io_bazel_rules_closure//closure:defs.bzl", "closure_repositories")

closure_repositories()

We must check the bazel version before trying to parse any other BUILD

files, in case the parsing of those build files depends on the bazel

version we require here.

load("//tensorflow:version_check.bzl", "check_bazel_version_at_least")
check_bazel_version_at_least("0.10.0")

load("//tensorflow:workspace.bzl", "tf_workspace")

load("//third_party/android:android_configure.bzl", "android_configure")
android_configure(name="local_config_android")
load("@local_config_android//:android.bzl", "android_workspace")
android_workspace()

Please add all new TensorFlow dependencies in workspace.bzl.

tf_workspace()

new_http_archive(
name = "inception_v1",
build_file = "models.BUILD",
sha256 = "7efe12a8363f09bc24d7b7a450304a15655a57a7751929b2c1593a71183bb105",
urls = [
"http://storage.googleapis.com/download.tensorflow.org/models/inception_v1.zip",
"http://download.tensorflow.org/models/inception_v1.zip",
],
)

new_http_archive(
name = "mobile_ssd",
build_file = "models.BUILD",
sha256 = "bddd81ea5c80a97adfac1c9f770e6f55cbafd7cce4d3bbe15fbeb041e6b8f3e8",
urls = [
"http://storage.googleapis.com/download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_android_export.zip",
"http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_android_export.zip",
],
)

new_http_archive(
name = "mobile_multibox",
build_file = "models.BUILD",
sha256 = "859edcddf84dddb974c36c36cfc1f74555148e9c9213dedacf1d6b613ad52b96",
urls = [
"http://storage.googleapis.com/download.tensorflow.org/models/mobile_multibox_v1a.zip",
"http://download.tensorflow.org/models/mobile_multibox_v1a.zip",
],
)

new_http_archive(
name = "stylize",
build_file = "models.BUILD",
sha256 = "3d374a730aef330424a356a8d4f04d8a54277c425e274ecb7d9c83aa912c6bfa",
urls = [
"http://storage.googleapis.com/download.tensorflow.org/models/stylize_v1.zip",
"http://download.tensorflow.org/models/stylize_v1.zip",
],
)

new_http_archive(
name = "speech_commands",
build_file = "models.BUILD",
sha256 = "c3ec4fea3158eb111f1d932336351edfe8bd515bb6e87aad4f25dbad0a600d0c",
urls = [
"http://storage.googleapis.com/download.tensorflow.org/models/speech_commands_v0.01.zip",
"http://download.tensorflow.org/models/speech_commands_v0.01.zip",
],
)

android_sdk_repository(
name = "androidsdk",
api_level = 23,
build_tools_version = "25.0.1",
# Replace with path to Android SDK on your system
path = "/opt/Android/Sdk/",
)
android_ndk_repository(
name="androidndk",
path="/home/user/Desktop/android-ndk-r13b/",
api_level=14)

when i ran the bazel command bazel build -c opt //tensorflow/contrib/android:libtensorflow_inference.so --crosstool_top=//external:android/crosstool --host_crosstool_top=@bazel_tools//tools/cpp:toolchain --cpu=armeabi-v7a i get the following error:

ERROR: /home/user/tensorflow/tensorflow/core/BUILD:2306:1: C++ compilation of rule '//tensorflow/core:protos_all_proto_cc_impl' failed (Exit 1)
In file included from bazel-out/armeabi-v7a-opt/genfiles/tensorflow/core/framework/function.pb.cc:4:
In file included from bazel-out/armeabi-v7a-opt/genfiles/tensorflow/core/framework/function.pb.h:9:
In file included from external/protobuf_archive/src/google/protobuf/stubs/common.h:52:
In file included from external/protobuf_archive/src/google/protobuf/stubs/mutex.h:33:
In file included from external/androidndk/ndk/sources/cxx-stl/gnu-libstdc++/4.9/include/mutex:35:
external/androidndk/ndk/sources/cxx-stl/gnu-libstdc++/4.9/include/bits/c++0x_warning.h:32:2: error: This file requires compiler and library support for the ISO C++ 2011 standard. This support is currently experimental, and must be enabled with the -std=c++11 or -std=gnu++11 compiler options.
#error This file requires compiler and library support for the
^
In file included from bazel-out/armeabi-v7a-opt/genfiles/tensorflow/core/framework/function.pb.cc:4:
In file included from bazel-out/armeabi-v7a-opt/genfiles/tensorflow/core/framework/function.pb.h:9:
In file included from external/protobuf_archive/src/google/protobuf/stubs/common.h:52:
external/protobuf_archive/src/google/protobuf/stubs/mutex.h:58:8: error: no type named 'mutex' in namespace 'std'
std::mutex mu_;

In file included from bazel-out/armeabi-v7a-opt/genfiles/tensorflow/core/framework/function.pb.cc:4:
In file included from bazel-out/armeabi-v7a-opt/genfiles/tensorflow/core/framework/function.pb.h:9:
In file included from external/protobuf_archive/src/google/protobuf/stubs/common.h:53:
external/protobuf_archive/src/google/protobuf/stubs/callback.h:346:25: error: no type named 'remove_reference' in namespace 'std'
typedef typename std::remove_reference<T>::type base_type;
        ~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~
external/protobuf_archive/src/google/protobuf/stubs/callback.h:346:41: error: expected member name or ';' after declaration specifiers
typedef typename std::remove_reference<T>::type base_type;
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
external/protobuf_archive/src/google/protobuf/stubs/callback.h:347:17: error: unknown type name 'base_type'
typedef const base_type& type;
              ^
external/protobuf_archive/src/google/protobuf/stubs/callback.h:401:17: error: no type named 'remove_reference' in namespace 'std'
typename std::remove_reference<P1>::type p1_;
~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~
external/protobuf_archive/src/google/protobuf/stubs/callback.h:401:33: error: expected member name or ';' after declaration specifiers
typename std::remove_reference<P1>::type p1_;
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
external/protobuf_archive/src/google/protobuf/stubs/callback.h:402:17: error: no type named 'remove_reference' in namespace 'std'
typename std::remove_reference<P2>::type p2_;
~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~
external/protobuf_archive/src/google/protobuf/stubs/callback.h:402:33: error: expected member name or ';' after declaration specifiers
typename std::remove_reference<P2>::type p2_;
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
external/protobuf_archive/src/google/protobuf/stubs/callback.h:403:17: error: no type named 'remove_reference' in namespace 'std'
typename std::remove_reference<P3>::type p3_;
~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~
external/protobuf_archive/src/google/protobuf/stubs/callback.h:403:33: error: expected member name or ';' after declaration specifiers
typename std::remove_reference<P3>::type p3_;
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
external/protobuf_archive/src/google/protobuf/stubs/callback.h:404:17: error: no type named 'remove_reference' in namespace 'std'
typename std::remove_reference<P4>::type p4_;
~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~
external/protobuf_archive/src/google/protobuf/stubs/callback.h:404:33: error: expected member name or ';' after declaration specifiers
typename std::remove_reference<P4>::type p4_;
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
external/protobuf_archive/src/google/protobuf/stubs/callback.h:405:17: error: no type named 'remove_reference' in namespace 'std'
typename std::remove_reference<P5>::type p5_;
~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~
external/protobuf_archive/src/google/protobuf/stubs/callback.h:405:33: error: expected member name or ';' after declaration specifiers
typename std::remove_reference<P5>::type p5_;
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
external/protobuf_archive/src/google/protobuf/stubs/callback.h:383:9: error: member initializer 'p1_' does not name a non-static data member or base class
      p1_(p1),
      ^~~~~~~
external/protobuf_archive/src/google/protobuf/stubs/callback.h:384:9: error: member initializer 'p2_' does not name a non-static data member or base class
      p2_(p2),
      ^~~~~~~
external/protobuf_archive/src/google/protobuf/stubs/callback.h:385:9: error: member initializer 'p3_' does not name a non-static data member or base class
      p3_(p3),
      ^~~~~~~
external/protobuf_archive/src/google/protobuf/stubs/callback.h:386:9: error: member initializer 'p4_' does not name a non-static data member or base class
      p4_(p4),
      ^~~~~~~
fatal error: too many errors emitted, stopping now [-ferror-limit=]
20 errors generated.
Target //tensorflow/contrib/android:libtensorflow_inference.so failed to build
Use --verbose_failures to see the command lines of failed build steps.



how to solve this issue?