Thoughts on data science, statistics and machine learning.

Effective Train/Test Stratification for Object Detection

There’s an unavoidable, inherent difficulty in fine-tuning deep neural networks for specific tasks. Primarily, it stems from the lack of training data. To a layperson it would seem ridiculous that a pretrained vision model (containing millions of parameters, trained on millions of images) could learn to solve highly specific problems. Therefore, when fine-tuned models do perform well, they seem all the more miraculous. But on the other hand, we also know that it is easier to move from the general or the abstract to the specific, than the reverse.

Read more...

A Process for Readable Code

I took a course on data structures and algorithms over the last few months. It is being offered as a part of IIT Madras' Online Degree Program in Data Science and Programming, taught by Prof Madhavan Mukund. The program is a MOOC in a true sense, with tens of thousands of students enrolling each year. The DSA course itself is offered every trimester, and sees an average of ~700 enrollments every time.

Read more...

Rabies, Laziness & Privilege

It was the night of the recent 5-state assembly elections. One of my company’s clients is a major news channel, and I was at the studio late into the night, until the election commission announced that they had cancelled their press conference which was supposed to make an announcement about the final vote counts in Madhya Pradesh. A colleague offered to drop me home, and I got off at the gate of my colony, not wanting to subject my colleague to navigating the labyrinth that is any gated colony in South Delhi.

Read more...

Weighted Loss Functions for Instance Segmentation

This post is a follow up to my talk, Practical Image Classification & Object Detection at PyData Delhi 2018. You can watch the talk here: and see the slides here. I spoke at length about the different kinds of problems in computer vision and how they are interpreted in deep learning architectures. I spent a fair bit of time on instance and semantic segmentation (for an introduction to these problems, watch Justin Johnson’s lecture from the Stanford CS231 course here).

Read more...

Page 1 of 3