The DeepFace model was trained on the VGGFace2 dataset. 2D face alignment operation using Dlib's frontal face (HOG based) detector, 5 point facial landmarks and get_face_chips function were performed on the images to normalise inputs into the network. The pre trained weights of the Keras CNN model are downloadable in the form of .h5 files.

^*The VGGFace2 dataset (publicly available training set) was used for training such that 3 images from each of the classes were left for the hold-out dev-validation set. The aforementioned alignment technique accounted for removal of a lot of images contained in the original VGGFace2 dataset as HOG face detector could not detect faces that lacked frontal pose.