Lukas's starred repositories
testing-ml
Learn how to create reliable ML systems by testing code, data and models.
seldon-core
An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
github-action-markdown-link-check
Check all links in markdown files if they are alive or dead. 🔗✔️
albumentations
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
ControlNet
Let us control diffusion models!
gin-config
Gin provides a lightweight configuration framework for Python
understanding-the-python-ecosystem
This project focuses on understanding the language ecosystem
hydra-wandb-sweeper
WandB sweeps integration with Hydra sweeper
lazypredict
Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning
obsidian-ava
Quickly format your notes with ChatGPT in Obsidian
hlb-CIFAR10
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
comparing-automatic-augmentation-blog
Comparing four automatic image augmentation techniques in PyTorch: AutoAugment, RandAugment, AugMix, and TrivialAugment
small-text
Active Learning for Text Classification in Python
surgeon-pytorch
A library to inspect and extract intermediate layers of PyTorch models.
contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).
torchscale
Foundation Architecture for (M)LLMs
ppo-implementation-details
The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization