Vladimir Osin
where else to find them
github:osin-vladimir
linkedin:vosin
what they talk about
where they keep going back
- PyData Eindhoven4 editions2019–2023
on a stage with
- Milan Muljionce
who talks about the same things
- Alejandro Saucedo33 talks
- Robert Crowe12 talks
- Tobias Sterbak4 talks
- Simon Mo7 talks
- Bharath Reddy Baddam2 talks
- Merve Noyan11 talks
| title | conference | date |
|---|---|---|
| Taming the Machine: Basics of ML Models Training and Inference Optimization | PyData Eindhoven 2023 | 2023-11-30 |
Covers concrete knobs and measured wins: mixed precision (≈3× speedup, sometimes 5×), batch-size + optimizer tuning, gradient accumulation and checkpointing to… | ||
| MLOPS 101: Tips, Tricks and Best Practices | PyData Eindhoven 2021 | 2021-11-12 |
A practical checklist replaces hype with actions scoping asks the questions that kill 80% of ML projects at scoping by forcing clear success metrics and data… | ||
| Understanding Deep Neural Networks | PyData Eindhoven 2020 | 2020-10-07 |
Clear claims and concrete tools: model attributions use captum on a pretrained ResNet50 with top‑3 outputs, showing gradients (saliency, input×gradient, guided… | ||
| Managing Machine Learning Lifecycle with MLflow | PyData Eindhoven 2019 | 2019-11-16 |
Walks through MLflow setup, shows tracking server (SQLite backend + artifact store), records experiments from PyTorch training on Kuzushiji‑MNIST and logs… | ||
| nothing matches | ||