Flower Classification with Various Deep Learning Models

This project demonstrates the classification of flower images using several pre-trained deep learning models. The models used in this project include ResNet-50, VGG, InceptionV3, MobileNet, and Fine-tuning techniques for each model.

Files Overview

1. RESNET_50_FLOWER_CLASSIFICATION_(1).ipynb

This Jupyter notebook implements flower classification using the ResNet-50 model. The notebook includes data preprocessing, model training, and evaluation.

2. VGG_FLOWER.ipynb

This notebook uses the VGG model for flower classification. It covers the process of loading the VGG model, fine-tuning it for flower classification, and evaluating the results.

3. inception_FLOWER_CLASSIFICATION.ipynb

This notebook implements flower classification using the InceptionV3 model. It also includes model training and evaluation steps.

4. mobilenet_finetuning.ipynb

In this notebook, MobileNet is fine-tuned for flower classification. It shows how to adjust the MobileNet model for specific use cases and improve accuracy.

5. tqdm_inceptionv3_recognition.ipynb

This notebook uses InceptionV3 for flower image recognition with progress bars using the tqdm library to track the training process.

Requirements

The following libraries are required to run this project:

• TensorFlow or Keras (for deep learning models)
• tqdm (for progress tracking)
• NumPy
• Matplotlib
• Pandas

Install them using pip: