Shell-Edunet Skills4Future Internship (Jan 2025 - Feb 2025)

Project Overview

This project is part of the Shell-Edunet Skills4Future Internship program, which spans four weeks from January 2025 to February 2025. The primary objective of this project is to develop a Convolutional Neural Network (CNN) model to classify images of plastic waste into different categories.

Dataset

The dataset used for this project is sourced from Kaggle and can be accessed here. It contains images of plastic waste categorized into different classes.

What I Did in This Project

1. Data Preprocessing:

   • Loaded and explored the dataset to understand its structure and distribution.
   • Performed data cleaning and augmentation to enhance the dataset's quality and diversity.

2. Model Development:

   • Built a Convolutional Neural Network (CNN) model using TensorFlow and Keras.
   • Configured the model architecture with multiple convolutional layers, pooling layers, and dense layers to effectively capture features from the images.

3. Model Training:

   • Split the dataset into training and validation sets.
   • Trained the CNN model on the training set and validated its performance on the validation set.
   • Utilized techniques such as early stopping and learning rate scheduling to optimize the training process.

4. Model Evaluation:

   • Evaluated the model's performance using metrics such as accuracy, precision, recall, and F1-score.
   • Visualized the model's performance through confusion matrices and classification reports.

5. Results and Analysis:

   • Analyzed the model's predictions and identified areas for improvement.
   • Documented the findings and insights gained from the project.

Repository Structure

• README.md: Project overview and documentation.
• wasteclassification.ipynb: Jupyter notebook containing the code for data preprocessing, model development, training, and evaluation.

Conclusion

This project provided valuable hands-on experience in developing and deploying a CNN model for image classification tasks. The skills and knowledge gained from this project will be instrumental in future machine learning and data science endeavors.

For more details, please refer to the wasteclassification.ipynb file in this repository.