Congratulations Stefan, "Kaggle for robotics" seems like an exciting direction! I still remember your kindness and just wanted to wish you the best.
436 karma · joined May 28, 2019
Unbelievable and shameless.
(Edit: The article did not include its note on Fenwick trees when I commented this.)
It seems like the main learning curve for learning D3 is deeply understanding the underlying web technologies (looking at you SVG), so could something D3-like have a more abstracted renderer?
Anyway, once you use Observable - Jupyter notebooks are forever ruined, which is the highest praise I can give. Thanks for all your hard work Mike!
[0] https://observablehq.com/@unkleho/introducing-d3-render-trul...
How did the research process work while developing a book?
Detectron was open sourced in 2018. R-CNN didn't have any public implementations (there was later a Keras implementation that didn't get the same performance as the paper reported). TensorFlow models added some object detection models a few days after I started my internship, but had various issues at the time. SSD and YOLO both had public implementations, YOLO's being in it's own C based framework.
It's a completely different landscape three years later.
I worked at Starsky Robotics as a perception team intern after graduating high school. I will always be grateful for the team for the opportunity, it was a fantastic first job and everyone who worked there was very kind (especially Stefan).
Unfortunately, Starsky had effectively had no machine learning in 2017 (when I worked there), using solely classical computer vision techniques. This didn't match the company's ambitions of not using LIDAR and there was a strong stigma against switching to a deep learning approach. At the time, very few object detection models had public implementations and I spent a lot of time trying to get a YOLO9000 and RetinaNet implementations running at real-time speeds. Frustrating, as a small startup the labeling services kept screwing us over by returning poorly annotated images.
I think what I took away from the experience is that deep learning in domains with long tails requires a enormous investment in a labeling pipeline - dwarfing the computational aspect - to get decent results. I don't think any solutions are on the horizon that will allow us to bypass this reality. You don't see improvements between Comma.ai and Tesla because it's about the improvements far out on the tail.