ShapeNet

The ShapeNet package provides a PyTorch implementation of our paper “Super-Realtime Facial Landmark Detection and Shape Fitting by Deep Regression of Shape Model Parameters”.

It cointains:

• JIT
  • Layer
    • HomogeneousShapeLayer
    • HomogeneousTransformationLayer
    • _HomogeneousTransformationLayerPy
    • ShapeLayer
  • AbstractShapeNetwork
  • AbstractFeatureExtractor
  • Conv2dRelu
  • Img224x224Kernel7x7SeparatedDims
  • Networks
• Layer
  • ShapeLayer
  • _ShapeLayerPy
  • _ShapeLayerCpp
  • HomogeneousTransformationLayer
  • _HomogeneousTransformationLayerPy
  • _HomogeneousTransformationLayerCpp
  • Homogeneous Shape Layer
• Networks
  • AbstractShapeNetwork
  • AbstractFeatureExtractor
  • Conv2dRelu
  • Img224x224Kernel7x7SeparatedDims
  • Single Shape Network
  • Utilities
• Scripts
  • prepare_all_data
  • prepare_helen_dset
  • prepare_lfpw_dset
  • prepare_cat_dset
  • _prepare_ibug_dset
  • _prepare_cats
  • _process_single_cat_file
  • _make_pca
  • Training
  • Prediction
  • create_jit_net_from_config_and_weight
  • main
• Utilities
  • Config
  • Date-Time