/Melanoma_Predictor

A project meant to teach me the basics of CNN (Convolutional Neural Networks).

Primary LanguageJupyter NotebookMIT LicenseMIT

Melanoma_Predictor

A project meant to teach me the basics of CNN (Convolutional Neural Networks). The latest model is able to predict malignant melanomas (skin cancer) with about 90% accuracy.

Required libraries

  • tensorflow
  • numpy
  • cv2
  • matplotlib
  • keras

Usage

To use this project, follow these steps:

  1. Clone the repository: git clone https://github.com/congiants/Melanoma_Predictor.git
  2. Install the required libraries: pip install required_library
  3. The models are already trained and can be used. The two images in the root of the directory can be used for a quick test of the models
  4. The models can also be trained on a different dataset

Dataset

Dataset used from Kaggle: https://www.kaggle.com/datasets/hasnainjaved/melanoma-skin-cancer-dataset-of-10000-images

License

MIT License Copyright (c) 2023 Constantine Giantselidis

Dedication

This project is dedicated to my late grandmother, Sofia Gargavani, who was taken away by this form of cancer.