Dynamic Image Classifier

The Dynamism Classifier workflow predicts the degree of dynamism embedded in images. It was developed using more than 8,000 annotated images from social media, and a deep learning process involving deep learning and the ResNet50 architecture. It is an evolving product and so far reached an average accuracy of 81.4% on a 10-fold cross validated sample.

Last edited  Mar 7, 2023 8:39 PM