TFDroid | A simple demo for using Tensorflow models in Android apps | Android library

by omimo Java Version: Current License: MIT

X-Ray Key Features Code Snippets Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | TFDroid Summary

TFDroid is a Java library typically used in Mobile, Android, Tensorflow applications. TFDroid has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has low support. You can download it from GitHub.

A simple demo for using Tensorflow models in Android apps.

Support

Quality

Security

License

Reuse

Support

TFDroid has a low active ecosystem.

It has 86 star(s) with 39 fork(s). There are 10 watchers for this library.

It had no major release in the last 6 months.

There are 4 open issues and 2 have been closed. On average issues are closed in 1 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of TFDroid is current.

Quality

TFDroid has 0 bugs and 0 code smells.

Security

TFDroid has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

TFDroid code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

TFDroid is licensed under the MIT License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

TFDroid releases are not available. You will need to build from source code and install.

Build file is available. You can build the component from source.

TFDroid saves you 64 person hours of effort in developing the same functionality from scratch.

It has 168 lines of code, 3 functions and 10 files.

It has low code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed TFDroid and discovered the below as its top functions. This is intended to give you an instant insight into TFDroid implemented functionality, and help decide if they suit your requirements.

Initializes the model

Get all kandi verified functions for this library.

TFDroid Key Features

No Key Features are available at this moment for TFDroid.

TFDroid Examples and Code Snippets

No Code Snippets are available at this moment for TFDroid.

Community Discussions

Trending Discussions on TFDroid

Using a image_ocr tensorflow model from Keras Examples on Android

QUESTION

Using a image_ocr tensorflow model from Keras Examples on Android

Asked 2017-May-23 at 19:50

I'm trying to figure out how to use a tensorflow model from training the image_ocr example in Keras on Android. I've followed this tutorial in creating a tensorflow model (i.e. freezing the graph to creata a .pb file) to be used by the application.

The examples in TFDroid are pretty good but none of them seem to be applicable with the model I have. I have a few questions for now:

What are the things to consider when you're going to use a model of your own on Android?
What's the workflow from training a tensorflow model to using it on Android?

...

ANSWER

Answered 2017-May-23 at 19:50

I'm working on better documentation around this, but for now here's an extract from my current draft that may help:

In most situations, training a model with TensorFlow will give you a folder containing a GraphDef file (usually ending with the .pb or .pbtxt extension) and a set of checkpoint files. What you need for mobile or embedded deployment is a single GraphDef file that’s been ‘frozen’, or had its variables converted into inline constants so everything’s in one file. To handle the conversion, you’ll need the freeze_graph.py script, that’s held in tensorflow/pythons/tools/freeze_graph.py. You’ll run it like this:

Source https://stackoverflow.com/questions/44017591

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install TFDroid

You can download it from GitHub.
You can use TFDroid like any standard Java library. Please include the the jar files in your classpath. You can also use any IDE and you can run and debug the TFDroid component as you would do with any other Java program. Best practice is to use a build tool that supports dependency management such as Maven or Gradle. For Maven installation, please refer maven.apache.org. For Gradle installation, please refer gradle.org .