/image_classification_transfer_learning

This project involves using transfer learning to classify images into categories such as cats vs. dogs by leveraging a pre-trained model like VGG16 or ResNet. Transfer learning allows you to adapt a pre-trained model to your specific problem, making the training process faster and often more effective.

Primary LanguagePythonMIT LicenseMIT

Image Classification with Transfer Learning

This project utilizes transfer learning to classify images into categories using a pre-trained VGG16 model. Transfer learning allows us to leverage the features learned by the VGG16 model on the ImageNet dataset to improve classification performance on a new dataset.

Project Structure

  • data/: Contains scripts for loading and preprocessing image data.
  • model/: Contains the transfer learning model definition.
  • scripts/: Contains scripts for training and evaluating the model.
  • requirements.txt: Lists the required Python packages.

Getting Started

Open Colab file

OR

  1. Clone the repository:

    git clone https://github.com/coderooz/image_classification_transfer_learning.git
    cd image_classification_transfer_learning
  2. Install dependencies:

    pip install -r requirements.txt
  3. Prepare your dataset: Place your image data in data/train/ and data/validation/ directories, with subdirectories for each class.

  4. Train the model:

    python scripts/train_model.py
  5. Evaluate the model:

    python scripts/evaluate_model.py

Results

The model's accuracy on the validation set will be printed after evaluation.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements

Contact