Date
Tuesday, 06 Nov 2018 7:00 PM
Goal: To learn and apply deep learning techniques to computer vision
Roadmap: The following techniques will be covered in 4 different sessions
1) Classification
2) Object detection
3) Object localization
4) Instance Segmentation
Agenda – 1st session
a) What are Convolutional Neural Networks (CNN)?
b) How does classification work in a CNN?
c) Hands-on workshop for classification
Speaker: Anand Kadumberi, Data Scientist
Environment setup
https://www.linkedin.com/pulse/setting-up-python-environment-data-science-machine-keras-kadumberi/
Pre-requisites:
1. Elementary proficiency in python.
2. A system with GPU (cloud/laptop/desktop) for hands-on workshop
3. Software – Anaconda 3, tensorflow-gpu, keras, opencv-python, jupyter lab
Tutorial or Books recommended
1. Standford lectures – Convolutional Neural Networks for Visual Recognition (https://www.youtube.com/playlist?list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv).
2. Deep learning (Ian Goodfellow)
3. Deep learning with python (Francois Chollet)