2026
Fastest Matrix NMS in the West (Part 2): Going Down to CUDA
A faster Matrix NMS implementation using custom CUDA kernels.
Solving Azur Lane's Auction Game
I got obsessed with a minigame then I tried to solve it.
2022
From ResNet to ConvNeXt (Part 2): Modernizing a Vanilla ResNet
Progression from ResNet to ConvNeXt, step by step explained with code in PyTorch.
From ResNet to ConvNeXt (Part 1): ResNet with Better Training Techniques
Motivation of the ConvNeXt paper and a refresher on ResNet in PyTorch.