More than a framework
Machine Learning challenges
MLops ecosystem powered by open source
Convenient DL serving
Experiments monitoring
Accelerated DL & RL
Train
Analyze
Deploy
Catalyst.Ecosystem
Catalyst.Ecosystem
Eugene Kachan
Sergey Kolesnikov
David Kuryakin
Contributors�Researchers, Engineers
Artem Zolkin
Team
pip install catalyst
pip install alchemy
pip install reaction
PyTorch.Ecosystem
Tutorials
pip install catalyst
Sergey Kolesnikov, scitator@gmail.com
Extra
Catalyst.Reproducibility = 🖤
Catalyst has full DL & RL convergence tests for
DL, GANs and RL.
Catalyst.DL
Catalyst.Reproducibility = 🖤
DL pipelines reproducibility over different machines
Catalyst vs for-loop approach
VS
200+ lines!
Catalyst.RL
Catalyst.RL
Catalyst.RL
Comparison of catalyst.RL with a number of RL frameworks. �For a more detailed up-to-date table please check this Google Sheet.
Pseudo-Labeling is all you need
Anchor-free �object detection
Catalyst.Segmentation (semantic)
Catalyst.Segmentation (instance)
Temporal Segmentation Networks
Catalyst.GAN
Catalyst.NLP
ReAction
Bac Nguyen Xuan�Kaggle Competitions Master
Catalyst.Competitions – NeurIPS’18, 3rd place
Catalyst.Competitions – NeurIPS’19, 2nd place