markdown Copy code

Weather Classification with TensorFlow

This project demonstrates a weather classification model using TensorFlow, applied to four different datasets: ACDC, MWD, UAVid, and Syndrone. The notebook provides a step-by-step approach to build, train, and evaluate a machine learning model to classify weather conditions using these datasets.

Features

• Data preprocessing and augmentation for various weather datasets
• Neural network model development using TensorFlow
• Model training and evaluation across different datasets
• Comparison of model performance using loss graphs, accuracy graphs, and confusion matrices

Datasets

1. ACDC
2. MWD
3. UAVid
4. Syndrone

The project involves comparing the performance of the model across these datasets using different metrics:

• Loss Graphs: Shows the training and validation loss for each dataset.
• Accuracy Graphs: Displays the training and validation accuracy for each dataset.
• Confusion Matrices: Visualizes the model’s classification performance and confusion between classes for each dataset.

Usage

1. Clone the repository:

   git clone https://github.com/PooyaNasiri/weather-classification.git
   

Results

Visualizations and evaluation metrics like confusion matrices are provided in the notebook.