How mainakverse/dermopathy-ai works
Project type and purpose
• This is a machine‐learning–driven web application (built on Flask) for detecting and predicting types of skin diseases from uploaded images.
• The core use case is: User uploads an image → server runs inference with a pre‐trained model → returns disease classification.
File structure
• Top level:
• Disease Images/ ← directory of sample or training images
• app.py ← Flask application entry point, defines routes for upload and prediction
• config.toml ← application and model configuration (paths, parameters)
• requirements.txt ← Python dependencies (Flask, TensorFlow/Keras, etc.)
• skin disease detection.ipynb ← exploratory/development notebook
• skin.h5 ← pre‐trained Keras model
• README.md ← project description and dataset reference
• No separate “frontend” folder – likely uses simple HTML templates in Flask or returns JSON for a minimal UI.
• No explicit database; images may be processed in memory or stored in a local directory.
README for additional insights
• Confirms purpose: detect and predict skin disease from images.
• References a Kaggle dataset, but no explicit data‐loading code in the Flask app – preprocessing likely in the notebook and model saved as skin.h5.