Archive
Tags
Search
Consulting
Subscribe
Veritable Tech Blog
Technical Notes from a Data Geek.
[Notes] MaxViT: Multi-Axis Vision Transformer
Multi-axis attention to enable both local and global interactions efficiently
[Notes] PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
A simple tweak to make your loss function much more adaptable
[Notes] Understanding Visual Attention Network
Decompose large kernel convolutions to get attention weights efficiently
[Notes] Understanding ConvNeXt
A ConvNet for the 2020s
Use MPIRE to Parallelize PostgreSQL Queries
A case study for the high-level Python multiprocessing library
Older Posts
→