FeatureNet

This is a re-implementation of FeatureNet in Tensorflow 2. FeatureNet is a deep learning architecture for machining feature recognition that utilises a voxel representation and 3D CNN.

The code can be found on GitLab.

The code is based on this original paper. This paper's original code can be found here and dataset is available here.

Citation

@article{featurenet2018,
  Author = {Zhibo Zhang, PrakharJaiswal, Rahul Rai},
  Journal = {Computer-Aided Design},
  Title = {FeatureNet: Machining feature recognition based on 3D Convolution Neural Network},
  Year = {2018}
}

@article{featurenettensorflow2,
  Author = {Andrew R Colligan},
  Title = {FeatureNet Tensorflow 2},
  Journal = {https://gitlab.com/qub_femg/machine-learning/featurenet-tensorflow-2},
  Year = {2021}
}