Skip to content

ikathuria/python-to-ai

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

133 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Python to AI — Interactive Learning Platform

Live Site Deploy

A free, self-hostable tutorial platform taking you from Python basics to advanced AI — with live in-browser ML model demos powered by ONNX Runtime Web. No server required; everything runs in your browser.

Live: ikathuria.github.io/python-to-ai


Learning Path

# Module Topics Demo
0 Python Basics Data types, structures, functions, OOP
1 ML Basics NumPy, Pandas, data preprocessing
2 Supervised Learning Classification, regression, KNN, Decision Trees Live prediction demo
3 Unsupervised Learning K-Means clustering, PCA Cluster assignment demo
4 Recommendation Systems Content-based & collaborative filtering
5 Deep Learning PyTorch, backprop, IrisNet
6 Computer Vision CNNs, convolution, image classification 🎨 Colour classifier (ONNX)
7 Time Series Stationarity, ARIMA, LSTM forecasting
8 NLP Word2Vec, PMI, language models

Features

  • Live ONNX demos — 9 trained models run entirely in the browser (no server, no Python needed)
  • Interactive quizzes — 3 knowledge-check questions per topic with instant feedback
  • Copy buttons — one-click copy on every code block
  • "Try it yourself" — collapsible hints for hands-on exercises
  • Mobile responsive — hamburger nav, stacked layouts on small screens

Tech Stack

Layer Choice
Frontend Vanilla HTML/CSS/JS + Tailwind CDN
Model inference onnxruntime-web (runs in browser)
Syntax highlighting Highlight.js
Hosting GitHub Pages (free, always-on)

Running Locally

git clone https://github.com/ikathuria/python-to-ai.git
cd python-to-ai
python -m http.server 8000
# open http://localhost:8000

No build step, no Node.js, no dependencies needed to view the site.


Re-training / Exporting Models

The ONNX models in app/onnx_models/ were exported from the Jupyter notebooks in the repo root. To retrain the colour CNN:

pip install torch torchvision onnx onnxsim pillow numpy
python scripts/export_colour_cnn.py

For more tutorials

About

Different machine learning algorithms implemented to predict the outcomes of different datasets.

Topics

Resources

Stars

2 stars

Watchers

1 watching

Forks

Contributors