Welcome to the CNN in TensorFlow project! This repository contains a series of Jupyter notebooks that explore various techniques for building and optimizing Convolutional Neural Network (ConvNet) models tailored for image classification tasks.
This collection of notebooks focuses on:
- Data Preprocessing: Techniques to prepare and clean image data for training.
- Model Building: Constructing ConvNet architectures for different classification problems.
- Augmentation Techniques: Enhancing the training dataset through various augmentation methods to improve model robustness.
- Transfer Learning: Utilizing pre-trained models to boost performance on new tasks.
- Multi-Class Classification: Approaches to handle classification tasks involving more than two categories.
Explore the dataset used in this project: Dogs vs. Cats
These notebooks were created as part of the Deep Learning Specialization offered by DeepLearning.ai on Coursera.
Through this project, I have enhanced my skills in:
- Convolutional Neural Networks (ConvNets)
- Addressing Overfitting
- Data Augmentation using Keras ImageDataGenerator
- Implementing Dropout layers
- Building Multi-Class Classifiers
- Utilizing TensorFlow and Python for deep learning applications
The following notebooks are included in this repository:
- Cats vs Dogs Image Classifier
- Tackling Overfitting in Cats vs Dogs Classifier
- Pre-Trained Model for Cats vs Dogs Classifier
- Multi-Class Classifier for Sign Language
Feel free to contribute by forking the repository and submitting a pull request with your enhancements or bug fixes!
This project is licensed under the MIT License - see the LICENSE file for details.
Thank you for checking out my work! I hope you find it helpful in your deep learning journey.