-
 

Package Summary

Tags No category tags.
Version 0.0.5
License MIT
Build type CATKIN
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/tue-robotics/image_recognition.git
VCS Type git
VCS Version master
Last Updated 2024-05-05
Dev Status DEVELOPED
CI status No Continuous Integration
Released RELEASED
Tags No category tags.
Contributing Help Wanted (0)
Good First Issues (0)
Pull Requests to Review (0)

Package Description

The image_recognition_tensorflow_rqt package

Additional Links

No additional links.

Maintainers

  • Rein Appeldoorn

Authors

No additional authors.

RQT plugins for Tensorflow image recognition

Contains rqt plugins for training a neural network for object recognition using TensorFlow.

Train plugin

GUI Overview

This RQT plugin (http://wiki.ros.org/rqt) enables training a neural network to classify objects based on images using TensorFlow. The end result will be a trained TensorFlow graph and output labels as in https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py

How to

Prerequisites

Annotated data with label subdirs that contain image segments of the specified label, e.g. /tmp/object_recognition:

/tmp/object_recognition/:
drwxrwxr-x 2 rein rein 4,0K okt 18 21:22 apple
drwxrwxr-x 2 rein rein 4,0K okt 18 21:22 banana
drwxrwxr-x 2 rein rein 4,0K okt 18 21:22 choco_peanuts

/tmp/object_recognition/apple:
-rw-rw-r-- 1 rein rein 14K okt 18 21:22 2016-10-18-21-22-29.jpg
...

/tmp/object_recognition/banana:
-rw-rw-r-- 1 rein rein 16K okt 18 21:22 2016-10-18-21-22-37.jpg
...

/tmp/object_recognition/choco_peanuts:
-rw-rw-r-- 1 rein rein 8,6K okt 18 21:22 2016-10-18-21-22-43.jpg
...

This labeled data set can be created with use of the label RQT plugin in the image_recognition_rqt package. But, feel free to use any kind of tooling to create your own data set!

Training

Start the train GUI

rosrun image_recognition_tensorflow_rqt train_gui

GUI Overview

Set the images and output directory. For the example above, use /tmp/object_recognition as images directory

Dir picker

and for example /tmp as output directory.

Click the gear wheel in the right top of the GUI to set the batch size and the number of steps:

Step Size Batch Size

Once everything is configured, press the “Train” button.

Wait for some hours :) – Check console log.

CHANGELOG

\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^ Changelog for package image_recognition_tensorflow_rqt \^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^\^

0.0.5 (2019-06-08)

  • Added catkin lint to all packages
  • refactor package xml to 2.0
  • rename ROS pkgs with image_recognition_prefix
  • Contributors: Rein Appeldoorn

0.0.4 (2017-02-07)

0.0.3 (2017-02-07)

  • fix(): Add targets install for scripts
  • Contributors: Rein Appeldoorn

0.0.2 (2017-01-17)

  • fix(): Installation targets
  • Contributors: Rein Appeldoorn

0.0.1 (2017-01-17)

  • Added link in GUI to tensorboard
  • Tensorboard start while training
  • Added view tensorflow button
  • Documentation
  • Update README.md
  • Added imgs
  • Some minor reference and naming fixes
  • Renamed dir name and fixed plugin xml
  • Merged tensorflow_object_recognition_rqt into image_recognition repo, renamed to image_recognition_tensorflow_rqt
  • Contributors: Rein Appeldoorn

Wiki Tutorials

This package does not provide any links to tutorials in it's rosindex metadata. You can check on the ROS Wiki Tutorials page for the package.

Package Dependencies

Deps Name
catkin
image_recognition_tensorflow
rqt_gui
rqt_gui_py
python-sphinx-autoapi-pip
python-sphinx-rtd-theme-pip
catkin_lint_cmake

System Dependencies

Dependant Packages

Launch files

No launch files found

Messages

No message files found.

Services

No service files found

Plugins

Recent questions tagged image_recognition_tensorflow_rqt at Robotics Stack Exchange