Deep Learning Models for Facial Keypoints Detection.
The dataset has been taken from the Kaggle Competition Facial Keypoints Detection.
The objective of this task is to predict keypoint positions on face images. This can be used as a building block in several applications, such as:
- tracking faces in images and video
- analysing facial expressions
- detecting dysmorphic facial signs for medical diagnosis
- biometrics / face recognition
- Baseline Model - ResNet50 with pretrained weights
- Post Training Quantization