December 18, 2017
Two short talks and plenty of mingling for our December event. Sponsored by Twitter (https://careers.twitter.com/en/locations/boston.html).
Douglas Landgraf: Controlling a Surveillance Camera with Python
An overview of our project to control an Amcrest camera from Linux. Starting with the vendor SDK, we had some challenges like options not correctly documented, how to write a code for reuse, integration, reverse engineering, and so on. In the end, we extended the library to a shell CLI, a text user interface, and interfacing to Home Assistant, an open-source Python 3 home automation platform.
Gretchen Green: DragonPaint – Bootstrapping Small Data to Color Cartoons
The creation of sufficient quantities of labeled training data is one of the biggest challenges for machine learning applications, especially when the data itself must be created, not just labeled. DragonPaint presents a generalizable strategy for minimizing the manual creation of data using rule based algorithms to automate the creation of a restricted subset of data and then bootstrapping to the automated creation of unrestricted (rule breaking) training and test data. A gentle introduction to computer vision, graphics and machine learning, we use Python and geometry to build an image data set so we can use TensorFlow to train a model.
Meetup link: https://www.meetup.com/bostonpython/events/244941784/