TensorFlow

 TensorFlow is an open-source machine learning

library for research and production.
 TensorFlow™ is an open source software library
for high performance numerical computation.
 Its flexible architecture allows easy deployment of
computation across a variety of platforms (CPUs,
GPUs, TPUs), and from desktops to clusters of
servers to mobile and edge devices.
 TensorFlow offers APIs for beginners and experts
to develop for desktop, mobile, web, and cloud.
Installing TensorFlow on Windows

 64-bit, x86 desktops or laptops

 Windows 7 or later
 Install python, any one of the following version:
 Python 3.5.x 64-bit from python.org
 Python 3.6.x 64-bit from python.org
 TensorFlow supports Python 3.5.x and 3.6.x on
Windows.
 Python 3 comes with the pip3 package manager, which
is the program you'll use to install TensorFlow.
 To install TensorFlow, start a terminal
 Issue the appropriate pip3 install command in that
terminal.
Installing TensorFlow on Windows

 To install the CPU-only version of TensorFlow,

enter the following command:
 C:\> pip3 install --upgrade tensorflow
 To install the GPU version of TensorFlow, enter the
following command:
 C:\> pip3 install --upgrade tensorflow-gpu
Jupyter Notebook
 The Jupyter Notebook is an open-
source web application that allows you
to create and share documents that
contain live code, equations,
visualizations and narrative text.
 Uses include: data cleaning and
transformation, numerical simulation,
statistical modeling, data visualization,
machine learning, and much more.
Installing the Jupyter Notebook

 Prerequisite: Python
 While Jupyter runs code in many programming languages,
Python is a requirement (Python 3.3 or greater, or Python
2.7) for installing the Jupyter Notebook itself.
 Installing Jupyter using Anaconda:
 First, download Anaconda.
 Second, install the version of Anaconda which you
downloaded, following the instructions on the download
page.
 To run the notebook, run the following command at the
Terminal (Mac/Linux) or Command Prompt (Windows):
 jupyter notebook
 You should see the notebook open in your browser.
Installing the Jupyter Notebook
 Installing Jupyter with pip:
 If you have Python 3 installed (which is recommended):
 python3 –m pip install --upgrade pip
 python3 –m pip install jupyter.
 If you have Python 2 installed:
 python -m pip install --upgrade pip
 python -m pip install jupyter.
 To run the notebook, run the following command at the
Terminal (Mac/Linux) or Command Prompt (Windows):
 jupyter notebook
OpenCV
 OpenCV (Open Source Computer Vision Library) is an open
source computer vision and machine learning software library.
 OpenCV was built to provide a common infrastructure for
computer vision applications and to accelerate the use of
machine perception in the commercial products.
 The library has more than 2500 optimized algorithms, which
includes a comprehensive set of both classic and state-of-the-
art computer vision and machine learning algorithms.
 These algorithms can be used to detect and recognize faces,
identify objects, classify human actions in videos, track camera
movements, track moving objects, extract 3D models of objects,
produce 3D point clouds from stereo cameras, stitch images
together to produce a high resolution image of an entire
scene, find similar images from an image database, remove
red eyes from images taken using flash, follow eye
movements, recognize scenery and establish markers to
overlay it with augmented reality, etc.
OpenCV
 It has C++, Python, Java and MATLAB
interfaces and supports Windows,
Linux, Andriod and Mac OS.
 OpenCV leans mostly towards real-time
vision applications and takes advantage
of MMX and SSE instructions when
available.
SUMO
 "Simulation of Urban MObility", or "SUMO"
for short, is an open source, microscopic,
multi-modal traffic simulation.
 It allows to simulate how a given traffic
demand which consists of single vehicles
moves through a given road network. The
simulation allows to address a large set of
traffic management topics.
 It is purely microscopic: each vehicle is
modelled explicitly, has an own route, and
moves individually through the network.
FEATURES
 Includes all applications needed to prepare and perform a traffic simulation (network and routes import, DUA, simulation)
 Simulation
 Space-continuous and time-discrete vehicle movement
 Different vehicle types
 Multi-lane streets with lane changing
 Different right-of-way rules, traffic lights
 A fast openGL graphical user interface
 Manages networks with several 10.000 edges (streets)
 Fast execution speed (up to 100.000 vehicle updates/s on a 1GHz machine)
 Interoperability with other application at run-time
 Network-wide, edge-based, vehicle-based, and detector-based outputs
 Supports person-based inter-modal trips
 Network Import
 Imports VISUM, Vissim, Shapefiles, OSM, RoboCup, MATsim, OpenDRIVE, and XML-Descriptions
 Missing values are determined via heuristics
 Routing
 Microscopic routes - each vehicle has an own one
 Different Dynamic User Assignment algorithms
 High portability
 Only standard C++ and portable libraries are used
 Packages for Windows main Linux distributions exist
 High interoperability through usage of XML-data only
 Open source (EPL)
Usage Examples

 Since 2001, the SUMO package has been

used in the context of several national and
international research projects. The
applications included:
 traffic lights evaluation
 route choice and re-routing
 evaluation of traffic surveillance methods
 Simulation of vehicular communications.
 traffic forecast.