czeslov / weather-classification

This model classifies weather conditions based on images. It uses a Convolutional Neural Network (CNN) trained on various weather phenomena to predict the weather condition of a given image.

  • Public
  • 8 runs
Run with an API
Playground API Examples README Versions

Run time and cost

This model runs on Nvidia T4 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Weather Classification Model

This model classifies weather conditions from images using a deep learning approach. The model was trained on a dataset of various weather phenomena and can predict one of the following weather classes:

  • Dew
  • Fog/Smog
  • Frost
  • Glaze
  • Hail
  • Lightning
  • Rain
  • Rainbow
  • Rime
  • Sandstorm
  • Snow

Features:

  • Real-time predictions: Classifies weather images quickly, ideal for applications requiring fast response times.
  • Multiple classes: Can detect and classify 11 different weather conditions.
  • Efficient architecture: Optimized to be lightweight and fast, suitable for various platforms.

Usage:

Inputs:

  • Image: A single image of weather conditions. The image should be a .jpg, .png, or similar format and will be resized to 200x200 pixels before processing.

Output:

  • Predicted Class: The model will return the predicted weather class based on the image input