Mobilenet YoloMobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥
MtcnnMTCNN face detection implementation for TensorFlow, as a PIP package.
FacialLandmark TFFacial landmarks training by tensorflow. Use for face alignment and so on.
HyperLandmark-iOSA 68-point Facial landmark at 28-30 FPS on iPhone 6S+. HyperLandmark is get from https://github.com/zeusees/HyperLandmark.
ai for roboticsVisualizations of algorithms covered in Sebastian Thrun's excellent Artificial Intelligence for Robotics course on Udacity.
face ratingFace/Beauty Rating with both the traditional ML approaches and Convolutional Neural Network Approach