This repository focuses on the application of Convolutional Neural Network (CNN) architectures for the classification of skin lesions. Four popular CNN models, namely EfficientNet-B3, VGG16, DenseNet, and Inception V3, have been implemented and evaluated on a dataset of skin lesion images.
Models | Base Model | EfficientNet-B3 | VGG16 | DenseNet | Inception V3 |
---|---|---|---|---|---|
Data Augmentation | False | False | False | False | False |
Parameters | 85,867 | 10,783,535 | 14,716,227 | 12,647,875 | 21,808,931 |
Depth | 10 | 5 | 7 | 8 | 7 |
Validation | 68% | 72% | 68% | 73% | 71% |
Link | BM | EFB3 | VGG16 | IV3 |