From Albumentations to Image Search
Started with the feedback for Albumentations, ended with an image search..
Recent Posts
Albumentations: Feedback
Feedback for the Albumentations Library.
Unified Sports Classification System
Unified Sports Classification System.
The birth of Albumentations
About the birth and growth of the albumentations.
List of good non-fiction books that I have read in 2018-2021.
List of non-fiction books that helped me why working at Lyft (2018-2021).
YouDo Product Skills Track
A list of books to boost your Product Management skills.
I want to organize ML competition. Where is the playbook?
Organizing ML competions is not hard. Still, companies do not do it well.
Airbnb. Thanksgiving. Burglary.
Bad things happen. And sometimes it is not our fault.
I trained a model. What is next?
I wish I knew it when I was active at Kaggle.
Full version of the interview to Analytics India Magazine: Road To Machine Learning Mastery: Interview With Kaggle GM Vladimir Iglovikov.
This article is the full version of the interview with analyticsindiamag.com.
Multi-target in Albumentations
Many images, many masks, bounding boxes, and key points. How to transform them in sync?
Face recognition on 330 million faces at 400 images per second
Face detection, face recognition on 330 million faces at OK.Ru.
More hardware to the participants in Machine Learning competitions!
This article was originally posted at Medium.
Cross-post of the interview at hackernoon to Sanyam Bhutani
The interview qas originally published at hackernoon: Interview with Kaggle Grandmaster, Senior CV Engineer at Lyft: Dr. Vladimir I. Iglovikov.
Forensic Deep Learning: Kaggle Camera Model Identification Challenge
The importance of data augmentation