🔍 Debug ML With Overfitting: PyTorch Lightning (Tutorial + Example)

preview_player
Показать описание
⌛️ Save tons of time debugging machine learning models.
✅ Use overfitting to detect bugs quickly.
👩🏽‍💻. A concrete code example with PyTorch and Lightning

Debugging machine learning models can be hard and time consuming. Many thing can go wrong:
- A bug in data loading
- A bug in the mode itself
- A bug in the training loop
- ...
As bad as overfitting sounds, it can be your ally to debug machine learning models quickly. Let's see how!

Hope you'll enjoy it!

🔗 Socials:

00:00 Intro
00:21 What Is Overfitting?
01:53 How Overfitting Helps Debugging?
02:58 Code Demo Setup
03:24 Debug With Overfitting In PyTorch
06:46 Outro

Resources:
Рекомендации по теме
Комментарии
Автор

As always, great video! The illustrations are super well done and very helpful ! 💡Congratulations for your work 🦍🔥

mariegautier
Автор

Great work my bro you got my thumb up 🔥

natevaub
Автор

The note book didn't work since it requires configure_optimizers defined. Even with the definition, it still failed. Can you update the notebook?

kuangliangj