/DEX-Deep-Expectation-Network-used-for-age-estimation

The estimation of apparent age in still face images with deep learning uses the VGG-19 architecture. The age regression problem is posed as a deep classification problem followed by a softmax expected value refinement and show improvements over direct regression training of CNNs. Deep EXpectation (DEX) of apparent age, uses an ensemble of 3 (Original paper uses 20) VGG19 networks to predict the age

Primary LanguageJupyter Notebook

Watchers