-
Each session has it's own dedicated directory with a a README file, which would help to give an overview for that session.
-
minigrad
is an attempt to understand and have a minimalistic Auto-grad engine with capability to develop full working Neural Networks. Inspired from Andrej Karpathy's micrograd. Will keep understanding and adding more operations along with features as I go along. -
Extra resources like images or gifs would go under resources folder
-
Experiments will hold notebooks for sometimes session based tests or something different, but will revolve around CV.
VisionX: The main source for structured and modularised code, for ease of use and out of the box experimentation, work in progress
- Complete README for all existing session dirs
- Improve main README
- Implement Backward pass for minigrad and add more operations.