This second week, the proposed task was to execute and study the code of the Final Master Project of Marcos Pieras and the Final Grade Project of David Pascual. The code is available at their GitHub repositories https://github.com/RoboticsURJC-students/2015-TFM-Marcos-Pieras/tree/master/TrackingComponent (Marcos) and https://github.com/RoboticsURJC-students/2016-tfg-david-pascual (David).
Once you have downloaded the repositories, you need to open a new terminal and type:
-Marcos’ project:
python3 main.py
-David’s project:
cameraserver cameraserver.cfg
python digitclassifier.py digitclassifier.cfg
But, as expected, it is not so easy. First, I had to install all the necessary dependencies for each project which included Keras with Tensorflow and Theano backends following the installation process available at https://keras.io/#installation. After that I setup OpenCV and JdeRobot tools to work properly together.
To use Marcos’ project you need to download also the content included in https://github.com/balancap/SSD-Tensorflow which allows you to use the SSD VGG 300 net and other tools used in the project. Besides, you need to have the dataset to test the detection project, for example the MOT16-14 dataset (https://motchallenge.net/data/MOT16/#download), and the checkpoint used in the project (https://drive.google.com/file/d/0B0qPCUZ-3YwWT1RCLVZNN3RTVEU/view). I had some problems loading the checkpoint but I solved it using the information provided in https://github.com/tensorflow/tensorflow/issues/2999.
After the configuration made previously, David’s project should work fine but the Keras model used net_4conv_patience5.h5 was not available at his repository so I asked him personally and he is going to update the repository soon.
I could not finish the complete task yet but I hope to do it soon. Also to appreciate the friendly help of Marcos and David in this process :)