nn-template VS lightning-hydra-template

If I was starting a new project, I’d like to try using this cookiecutter template: https://github.com/grok-ai/nn-template

I would pick a project that interests you as that'll help you power through. If there's nothing that comes to mind, image classification is fairly standard. PyCaret does a lot but if you want to understand each of the tools you've listed, I'd recommend tackling each one separately. That being said, I don't think there's anything wrong starting with using a high level library and diving deeper as the need arises. If you do decide to build it piece by piece, it sometimes useful to have a library that'll help you start and remove the boilerplate of all of these tools. I came across a template repo which has a bunch of the tools you've listed which could be a good starting point: https://github.com/lucmos/nn-template

Link: https://github.com/lucmos/nn-template

I've been trying to learn PyTorch Lightning and Hydra in order to use/create my own custom deep learning template (e.g. like this) as it would greatly help with my research workflow. A lot of the work I do requires me to analyse metrics based on the logits/activations of the model.

I can't say for sure whether it is the best combination for research in the long run, but if you do go down that route I have found this template very useful

lightning-hydra-template

This lightning + hydra template is quite complete. Great for learning best practices.

A good example is this project template https://github.com/ashleve/lightning-hydra-template. It uses a lot of cool things such as

and many more! (checkout the #Your Superpowers section of the readme)

I write a LightningDatamodule. I found it to be an intuitive way to encapsulate any dataset. LightningDatamodule is a simple abstraction providing methods for data download, split, transforms and exposing dataloaders. Would love to see more researchers try out this concept, even in projects which don't use pytorch lightning. Reading LightningDatamodule makes me immedietely see how the dataset is prepared, while it seems like most data science projects throw around data logic across different parts of the pipeline, making it hard to understand what's going on. You can see example of such datamodule here

I feel like most ML people don't use those tools because they simply don't realize all the advantages (especially Hydra seems like a very useful addition to any deep learning project). I focused on structuring the readme in a way, which (I hope) will give you a quick overview - my hope is it can help to spread the word about those frameworks in a broaded community. It incorporates best practices and tricks I gathered over the last couple of months of playing around with it.