Painting with GANs: Challenges and Technicalities of Neural Style Transfer

Building Artistic Artefacts using Generative Networks

Anmol Krishan Sachdeva

Computer Vision Deep Learning Generative Adversarial Networks Image Processing Machine-Learning

See in schedule

A lot of advancements are happening in the field of Deep Learning and Generative Adversarial Networks are one of them. We have seen GANs being applied for photo editing and in-painting, generating new image datasets and realistic photographs, increasing resolution of images (Super Resolution), and many more things. Some people have also exploited GANs for generating fake content. All the above-mentioned examples are result of a technique where the focus is to generate uncommon yet original samples from scratch. However, these examples have very less commercial applications and GANs are capable of doing much more. The focus of this talk is a technique called "Neural Style Transfer (NST)" which has numerous commercial applications in the gaming world, fashion/design industry, mobile applications, and many more fields. Challenges and technicalities of NSTs will be covered in great detail. We will teach the machines on how to paint images and utilize Style Transfer networks to generate artistic artefacts.

The flow of the talk will be as follows:
~ Self Introduction [1 minute]
~ A Succinct Prelude to GANs [10 minutes]
~ Understanding Style Transfer [5 minutes]
~ Learning about Neural Style Transfer Networks [5 minutes]
~ Loss Functions: Content, Style, Total Variantion [10 minutes]
~ Code Walkthrough and Result Analysis [5 minutes]
~ Challenges and Applications [5 minutes]
~ Questions and Answers Session [3-4 minutes]

Type: Talk (45 mins); Python level: Intermediate; Domain level: Intermediate

Anmol Krishan Sachdeva

OLX Group, Naspers

Last year, I delivered talks at PyCon Thailand, GeoPython, and got invited to speak at EuroPython 2019 and PyCon Malaysia. The response was overwhelming. It was an honour to be part of such amazing events and communities. The connections that I made last year seems to be like life long contacts. I share a deep bond with the PyCon Community and hope for much more learning, exchange of ideas, excitement, and fun this year. I have been speaking at PyCon, EuroPython, and GeoPython for a few years now.

Compact Biography:
~ Currently, working as a Site Reliability Engineer at OLX Group, Naspers (one of the largest global online marketplaces).
~ MSc in Advanced Computing (Machine Learning, Artificial Intelligence, Robotics, Cloud Computing, and Computational Neuroscience), University of Bristol, United Kingdom.
~ International Tech Speaker (spoke at numerous prestigious National and International Conferences).
~ Distinguished Guest Lecturer at various renowned universities in India.
~ Spoke about Generative Adversarial Networks, Deep Fakes, and AI last year at PyCon Thailand ( and GeoPython (
~ Delivered a lot of talks and workshops on Kubernetes (, DevOps, and CI/CD too.
~ In past have spoken about "Recurrent Neural Networks and Long Short-Term Memory Networks (LSTMs)" at EuroPython, Edinburgh, Scotland - July 2018. Link: [Recurrent Neural Networks and Long Short-Term Memory Networks]( and "Understanding and Implementing Recurrent Neural Networks using Python" at GeoPython, Basel, Switzerland - May 18. Link: [Understanding and Implementing Recurrent Neural Networks using Python](
~ Have 8+ International Publications. [Latest work got published in ACM CHI. The project was exhibited in Montreal, Canada.]
~ Received 6 Honours and Awards (International and National level).
~ Represented India at International Hackathons like Hack Junction’16, Finland and Hack the North’16, Canada. Got invited for more than a ‘dozen’ of prestigious International Hackathons (PennApps’17, HackNY’17, Hack Princeton’17 and many more) and Conferences.
~ A Microsoft Certified Professional, Microsoft Technology Associate, IBM Certified Web Developer, and Hewlett Packard Certified Developer.
~ Former Software Developer Intern at IBM & an ALL STACK DEVELOPER capable of designing and developing solutions for Mobile, Web, Embedded Systems, and Desktop. Areas of interest are Computational Neuroscience, Deep Learning, Microservices, System Design, and Cloud Computing.