The tensorflow malaria dataset contains 27558 Images of classes "Parasitized" and "Uninfected" The aim of this project is to build a model using CNN as feature extractors toward improved parasite detection in thin blood smear images, to label them as "Parasitize" or "Uninfected."
The model achieved progressively lower training loss and higher training accuracy over five epochs, indicating effective learning from the training data. Additionally, consistent improvement in validation accuracy alongside stable validation loss suggests the model's ability to generalize well to unseen data.