Skip to content

A set of Jupyter notebooks for processing weather-related images and experimenting with different methods for image classification or analysis. Includes tools for loading, visualizing, and testing alternative approaches to improve model performance.

License

Notifications You must be signed in to change notification settings

Doremegalul/Weather_Images_Deep_Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Weather Images Deep Learning

This deep learning project trains AI models to classify road surface conditions (e.g., clear, light snow, medium snow, plowed) using roadside images and weather data. It tackles real-world problems in winter road monitoring with a custom dataset collected from public sources and weather APIs.

LoadWeatherImages.ipynb: Loads and preprocesses a dataset of road images and pairs them with historical weather data using image filenames and location-based API queries. Prepares training-ready data by resizing images, normalizing features, and structuring labels for classification.

Alternate_Method.ipynb: Implements a custom ResNet-based deep learning model for road condition classification. Uses image and weather data, applies data augmentation, and trains the model with the Adam optimizer and learning rate scheduling to improve generalization and performance.

About

A set of Jupyter notebooks for processing weather-related images and experimenting with different methods for image classification or analysis. Includes tools for loading, visualizing, and testing alternative approaches to improve model performance.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published