sample-tensorflow-imageclassifier | Classify camera images locally using TensorFlow | Computer Vision library

by androidthings Java Version: Current License: Apache-2.0

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

kandi X-RAY | sample-tensorflow-imageclassifier Summary

sample-tensorflow-imageclassifier is a Java library typically used in Artificial Intelligence, Computer Vision, Deep Learning, Tensorflow applications. sample-tensorflow-imageclassifier has no vulnerabilities, it has build file available, it has a Permissive License and it has low support. However sample-tensorflow-imageclassifier has 6 bugs. You can download it from GitHub.

When a button is pushed or when the touchscreen is touched, the current image is captured from the camera. The image is then converted and piped into a TensorFlow Lite classifier model that identifies what is in the image. Up to three results with the highest confidence returned by the classifier are shown on the screen, if there is an attached display. Also, the result is spoken out loud using Text-To-Speech to the default audio output. This project is based on the TensorFlow Android Camera Demo TF_Classify app and was adapted to use TensorFlow Lite, a lightweight version of TensorFlow targeted at mobile devices. The TensorFlow classifier model is MobileNet_v1 pre-trained on the ImageNet ILSVRC2012 dataset.

Support

Quality

Security

License

Reuse

Support

sample-tensorflow-imageclassifier has a low active ecosystem.

It has 625 star(s) with 196 fork(s). There are 49 watchers for this library.

It had no major release in the last 6 months.

There are 10 open issues and 8 have been closed. On average issues are closed in 110 days. There are 1 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of sample-tensorflow-imageclassifier is current.

Quality

sample-tensorflow-imageclassifier has 6 bugs (1 blocker, 0 critical, 4 major, 1 minor) and 22 code smells.

Security

sample-tensorflow-imageclassifier has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

sample-tensorflow-imageclassifier code analysis shows 0 unresolved vulnerabilities.

There are 1 security hotspots that need review.

License

sample-tensorflow-imageclassifier is licensed under the Apache-2.0 License. This license is Permissive.

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

Reuse

sample-tensorflow-imageclassifier 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.

Installation instructions, examples and code snippets are available.

sample-tensorflow-imageclassifier saves you 451 person hours of effort in developing the same functionality from scratch.

It has 1065 lines of code, 65 functions and 13 files.

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

Top functions reviewed by kandi - BETA

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

Called when an image is available
Converts a bitmap into a byte buffer
Looks to see if there are enough room to be played
Crop and resize the image
Initialize camera
Initializes the GPIO pins
Dumps all supported camera formats
Get the first available camera ID
Closes the background thread
Close the camera resources
Initialize the camera
Read labels from a file
Trigger a capture request
Loads a model file
Takes a camera photo
Handle key up

Get all kandi verified functions for this library.

sample-tensorflow-imageclassifier Key Features

No Key Features are available at this moment for sample-tensorflow-imageclassifier.

sample-tensorflow-imageclassifier Examples and Code Snippets

No Code Snippets are available at this moment for sample-tensorflow-imageclassifier.

Community Discussions

Trending Discussions on sample-tensorflow-imageclassifier

Android/Tensorflow converting Bitmap.getPixels to RGB pixel values results in colours not being correct

QUESTION

Android/Tensorflow converting Bitmap.getPixels to RGB pixel values results in colours not being correct

Asked 2018-Feb-05 at 01:15

I've built a image classifier using Tensorflow which I am running on Android using the Android Tensorflow library. My issue is that when classifying an image on Android the predicted class is completely off. But when classifying the image using Python with the same model the predicted class is correct.

The below method is how I am converting my bitmap into an array of RGB pixel values.(which I've taken from sample-tensorflow-imageclassifier and here).

...

ANSWER

Answered 2018-Feb-05 at 01:15

Turned out that the RGB channels were reversed by Bitmap.getPixels so changing to BGR worked.

Source https://stackoverflow.com/questions/48571112

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

Vulnerabilities

No vulnerabilities reported

Install sample-tensorflow-imageclassifier

On Android Studio, click on the "Run" button. If you prefer to run on the command line, type.
Wait until the LED turns on
Point the camera to something like a dog, cat or a furniture
Push the button to take a picture
The LED should go off while running. In a Raspberry Pi 3, it takes about 500 millisecond to capture the picture and run it through TensorFlow, and some extra time to speak the results through Text-To-Speech
Inference results will show in logcat and, if there is a display connected, both the image and the results will be shown
If a speaker or headphones are connected, the results will be spoken via text to speech

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: