Soft biometrics is a field in which a person’s gender, height, and weight are determined using a digital machine. This is due to the increasing number of real-world applications in day-to-day life with improved wireless technology. Soft biometrics generally consist of gender, age, ethnicity, height, and facial dimensions. In this paper, the authors propose a state-of-the-art Convolutional Neural Network (CNN) to classify gender and estimate age based on human face images. We also tune the hyperparameters of the CNN to compute the best result for the gender and age of a human face. Experimental results reveal that our proposed methodology achieved 82% accuracy for gender and 78% accuracy for age.