Last Sunday, I took a beginner’s session on getting started with artificial intelligence as part of AI-Creatives meetup Code & Coffee. To get the fancy of attendees, I picked up computer vision; more specifically, image recognition using deep learning.
As time was deliberately limited (90 mins), I focused on inference more than training. Deep learning, as you know, requires time (weeks to months) and resources (specialized GPUs). I based my demo on the Tensorflow’s image retraining tutorial.
The core idea was to quickly retrain a trained ImageNet model, and then create an API around it for inferences. This API would then be tested by using it on a webpage. I think the session went well. You can see the deck I used here. Source code for classifier, API and webpage is on GitHub.
Continue reading Celebrity Recognizer and Bulma
It was a good day spent at the cute little offices of Knowlarity. Nice to see so many others working on genuine artificial intelligence projects, at a time when AI is primarily being used to create demo-only applications meant to impress potential enterprise clients.
I think our presentation-cum-demo on improving a webpage’s accessibility through automatic image captioning was well-received with the audience. It was the same presentation that we’d used in Web4All’s 2018 conference in Lyon, France earlier this year. Shivam deserves much of the credit.
More info about the project:
A special thanks to Gaurav Gandhi for organising the event so well.
P.S. I didn’t know there were corporate offices inside Ambience Mall!