Magnus Petersen's starred repositories
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
DeepLearningExamples
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
kohya-trainer
Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning
conditional-flow-matching
TorchCFM: a Conditional Flow Matching library
schnetpack
SchNetPack - Deep Neural Networks for Atomistic Systems
stable-diffusion-aesthetic-gradients
Personalization for Stable Diffusion via Aesthetic Gradients 🎨
tiny-diffusion
A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.
se3-transformer-public
code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503
geometric-gnn-dojo
Geometric GNN Dojo provides unified implementations and experiments to explore the design space of Geometric Graph Neural Networks.
consistency_models
Unofficial Implementation of Consistency Models in pytorch
equiformer-pytorch
Implementation of the Equiformer, SE3/E3 equivariant attention network that reaches new SOTA, and adopted for use by EquiFold for protein folding
sketch-rnn-datasets
optional extra vector image datasets for sketch-rnn
recurrent-interface-network-pytorch
Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch
graph-transformer-pytorch
Implementation of Graph Transformer in Pytorch, for potential use in replicating Alphafold2
equiformer_v2
[ICLR'24] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
Reflected-Diffusion
[ICML 2023] Reflected Diffusion Models (https://arxiv.org/abs/2304.04740)
NeuralWaveMachines
Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks"
ops_tutorial
Introductory tutorial on TPS, committor analysis, and (MS)TIS with OpenPathSampling
sd-lazy-wildcards
sd-webui wildcards filled by LLM, no wordlist files required