/Aerial-Cactus-Identification

Trained a CNN model to classify cactus species (columnar cactus) in a binary classification challenge, hosted on Kaggle competition. Refined the model with image augmentation, pre-trained VGG16 model parameters using transfer learning, and improved the identification metric (area under ROC score) from 0.9964 to 0.9971 on the test set.

Primary LanguageJupyter Notebook

Stargazers

No one’s star this repository yet.