This repository contains the code and documentation for analyzing and classifying the Flowers102 dataset using transfer learning techniques. The main objective of this project is to experiment and compare different models based on various transfer learning approaches. Additionally, the team aimed to understand the different methodologies offered by each analyzed model, with a particular focus on a new paradigm called Big Transfer (BiT).

The dataset used for this project is Flowers102, which can be obtained from the following link: https://www.robots.ox.ac.uk/~vgg/data/flowers/102/. It consists of 102 categories of flower images, making it suitable for classification tasks.

The repository is structured as follows:

• Reports and Presentation/: This directory contains the reports and presentation files related to the project.
• notebooks/: This directory contains Jupyter notebooks used for data analysis, model training, and evaluation.
  • Flowers.ipynb: The main notebook that showcases the analysis, classification, and comparison of different transfer learning models.
• LICENSE: The license file for this repository.
• README.md: You are currently reading this file. It provides an overview of the repository and its contents.

Please refer to the respective directories and files for more details and specific instructions on running the code and reproducing the results.

To use this project, follow these steps:

1. Clone this repository to your local machine using the following command:

   git clone <repository-url>
   

2. Download the Flowers102 dataset from https://www.robots.ox.ac.uk/~vgg/data/flowers/102/ and place it in the appropriate directory.
3. Open the Jupyter notebooks in the notebooks/ directory to explore the analysis, classification, and comparison of transfer learning models.
4. Follow the instructions within the notebooks to run the code, train the models, and evaluate the results.