Revision as of 13:07, 12 November 2021

Goal

The goal is to create a new TensorFlow Object Detector by modifying Install Turtlebot3 Hood Waffle Foxy Tensorflow 20210615.

Sanity Test

Test Build

Build Passed

 $ cd tf_ws/

 $ colcon build --symlink-install
       Starting >>> ros2_tf_core
       Starting >>> tf_interfaces
       Finished <<< ros2_tf_core [1.46s]                                             
       Finished <<< tf_interfaces [2.40s]                     
       Starting >>> tf_classification_py
       Starting >>> tf_detection_py
       Finished <<< tf_detection_py [1.75s]                               
       Finished <<< tf_classification_py [1.79s]          
       Starting >>> ros2_tensorflow
       Finished <<< ros2_tensorflow [0.21s]                  

       Summary: 5 packages finished [4.66s]

Test Execution

Test Passed: Repeat Object Detection Task 2 in Install Turtlebot3 Hood Waffle Foxy Tensorflow 20210615 to make sure Foxy TensorFlow is not broken.

Add a New Server

Add the Server Code

Add a catsNdogs object detection server that does the same thing that the server does. It enables us to allows us to modify a new server without destroying any existing examples. We can then focus changes on the catsNdogs server.

 $ cd ~/tf_ws/src/ros2-tensorflow/tf_detection_py/tf_detection_py/examples

 $ cp server.py catsNdogs.py

Modify the Build Setup

 $ cd ../..

 $ cp setup.py setup.py.org

 $ emacs setup.py&

Add the catsNdoes detection server to the build.

eepp@hood:tf_detection_py$ diff setup.py.org setup.py 37a38 > 'catsNdogs = tf_detection_py.examples.catsNdogs:main',

Notes and Logs

• Turtlebot3 Waffle NUC Add TensorFlow Detect 20211107 Notes and Logs