How vruddhi18/quality-inspection works
Project type and purpose
• This is a small‐scale ML prototype + web UI for “quality inspection” of casting products.
• It includes a Jupyter notebook (data exploration + model training) and a Streamlit app (app.py) that loads the trained model and serves predictions via a simple user interface.
File structure
• Top‐level files only:
• Quality_inspection.ipynb – end‐to‐end data analysis & model training pipeline
• app.py – Streamlit web application for inference
• requirements.txt – Python dependencies (tensorflow, streamlit, streamlit-option-menu, etc.)
• README.md – project overview, instructions and external dataset link
• No multi‐service folders (e.g., no separate “backend” or “frontend” directories) → monolithic codebase
Key insights from the README
• Uses TensorFlow for model building
• Uses Streamlit + streamlit-option-menu to build the UI
• Uses localtunnel (via npx) to expose the local Streamlit server
• Data comes from an external Kaggle link