skin_lesion_classifier

Skin lesion classifier is my approach to problem presented in Deep Learning Udacity Course. It tries to classify skin lesion images into three different classes:

• Melanoma

• Nevus

• Seborrheic Keratosis

It has been build in python3.6 under the PyTorch framework.

For the proposed approach, based on Transfer Learning, I have chosen the VGG16 pre-trained on the ImageNet dataset (provided by PyTorch)

Data Sets

It has been used ISIC2017 dataset for trainning and testing

Install

It is suggested to use virtualenv (https://docs.python.org/3/tutorial/venv.html)

Then use pip to install the requirement:

pip install -r requirement.txt

Disclaimer

This project is just for reference and fun purposes. Additionally, I share it as a portfolio of my work.