A skin lesions classifier created using ResNet50 in keras, trained on HAM10000. Solved data imbalance by oversampling + data augmentation
Here's an intuitive explanation I wrote for how ResNet works & why it's used: https://medium.com/@realmichaelye/intuition-for-resnet-deep-residual-learning-for-image-recognition-39d24d173e78
- ResNet Model - https://arxiv.org/pdf/1512.03385.pdf
- Ham10000 Dataset - https://arxiv.org/ftp/arxiv/papers/1803/1803.10417.pdf