moleCare - CNN project

moleCare is an application that uses Convolutional Neural Networks (CNN) to classify images of skin moles as malignant or benign.

Some highlights:

We applied transfer learning and used the pre-trained MobileNet v2 model to train our data. Additional layers were added to fine tune our model.
The API was developed with Flask framework.
The application was built in a Docker, and the resulting Docker image was then deployed to Heroku.

Name		Name	Last commit message	Last commit date
Latest commit History 57 Commits
data		data
docker		docker
other notebooks		other notebooks
src		src
.gitignore		.gitignore
README.md		README.md
mole_detection.ipynb		mole_detection.ipynb