sradc/SmallPebble
A minimalist deep learning library written from scratch in Python
SmallPebble helps deep learning practitioners and students understand how deep learning frameworks work by providing a minimalist library for automatic differentiation and neural network training. It takes raw numerical data, like images or numbers, and processes them through neural network models. The output is a trained model and insights into the underlying mechanics of deep learning. It's ideal for those learning or teaching deep learning concepts.
132 stars. Available on PyPI.
Use this if you are a deep learning student, educator, or researcher who wants to learn, teach, or prototype core deep learning concepts from scratch without the complexity of production-grade frameworks.
Not ideal if you need a high-performance deep learning library for large-scale production deployments or require GPU acceleration.
Stars
132
Forks
14
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 19, 2026
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sradc/SmallPebble"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
davisking/dlib
A toolkit for making real world machine learning and data analysis applications in C++
ZigRazor/CXXGraph
Header-Only C++ Library for Graph Representation and Algorithms
mlpack/mlpack
mlpack: a fast, header-only C++ machine learning library
apache/singa
a distributed deep learning platform
hosseinmoein/DataFrame
C++ DataFrame for statistical, financial, and ML analysis in modern C++