Patrick Hiemsch 's starred repositories
ControlNet
Let us control diffusion models!
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
recommenders
Best Practices on Recommendation Systems
gaussian-splatting
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
the-algorithm-ml
Source code for Twitter's Recommendation Algorithm
Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
Dreambooth-Stable-Diffusion
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
pytorch-seq2seq
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
pandarallel
A simple and efficient tool to parallelize Pandas operations on all available CPUs
diffusion-models-class
Materials for the Hugging Face Diffusion Models Course
loss-landscape
Code for visualizing the loss landscape of neural nets
hlb-CIFAR10
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
minDiffusion
Self-contained, minimalistic implementation of diffusion models with Pytorch.
tiny-diffusion
A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.
modular-diffusion
Python library for designing and training your own Diffusion Models with PyTorch.
Deep-Eligibility-Traces
Implementation of Eligibility Traces with Neural Networks in PyTorch and Tensorflow 2.0
Data-Pipeline-with-dbt-using-Airflow-on-GCP
This project demonstrates how to build and automate an ETL pipeline using DAGs in Airflow and load the transformed data to Bigquery. There are different tools that have been used in this project such as Astro, DBT, GCP, Airflow, Metabase.
Youtube-video-data-analytics-using-AWS
This project aims to leverage Amazon Web Services to create trending Youtube videos analytics service. Project contains different data engineering, data analysis and data science parts.
scoota-app-clip
Master thesis project about fictional App Clip to rent an e-scooter
Master-Thesis
Master Thesis in Machine Learning