Body-mass index (BMI) is the amount of mass per area of a person, and it is an important indicator of the weight status. From health industry till the social media applications, there are many areas where BMI data is used. Various machine learning techniques are developed for BMI prediction only from a face image without any information about the weight and height of a person.Making this kind of predictions is a regression problem. In this study, a deep network based BMI predictor tool is designed and its performance is compared with the existing methods from previous studies. Additionally, a new data set for validation purposes is introduced.