alxyok's repositories
ai-physics
This project contains a collection of deep learning models developed by the AI4Sim team with various partners. This is is structured on the basis of use-cases providing canonical PyTorch Lightning pipelines allowing to train neural network models that are able to surrogate various physical processes.
aiphysx
Presentation of AI for Physics simulation. Pieces of knowledge accumulated over the years and serialized so nothing is lost.
alxyok
main()
argo-jupyter-scheduler
Extending Jupyter-Scheduler to use Argo-Workflows as a backend.
burgers
Neural solver to compute solutions to Burger's equation. 1D + 3D.
forkane
An experiment with Netflix's Metaflow framework.
kosmoss
Bootcamps for Deep Learning applied to a Weather Forecast UC: a) large dataset preprocessing, b) multi-node multi-GPU neural models training, and c) hyper-optimization
ransplacement
Rewrite of dataset build + model implementation + training logic from DDTM article by Ryley et al.
synthesis
A compilation of my understanding of deep learning applied to numerical simulation.
twitter-the-algorithm
Source code for Twitter's Recommendation Algorithm
westworld
Broken, unusable, useless, but fun code.