Hey everyone! π
I wanted to share MicroTorch, a lightweight tensor autograd engine and deep learning framework built from scratch in pure Python with zero external dependencies (no NumPy, no PyTorch).
π Key Features
- Reverse-Mode Autograd: Dynamic computation graph DAG with topological sort backpropagation.
-
N-Dimensional Tensors: Batched matrix multiplication (
@), broadcasting, and reduction operators. -
Modular Layers:
Linear,Sequential,ReLU,Sigmoid,Tanh,MSELoss,CrossEntropyLoss. -
Optimizers:
SGD(with momentum),Adam, andAdamW(with decoupled weight decay). - Visual Computation Graphs: ASCII trees and Mermaid diagrams.
Check out the code, architecture, and tests here:
π https://github.com/YashrajMiyatra/microtorch
Would love your thoughts, feedback, and stars on GitHub!
Top comments (0)