We use a neural network module dubbed EdgeConv suitable for CNN-based high-level tasks on point clouds including classification.
DGCNN
is the author's re-implementation of Dynamic Graph CNN, which achieves state-of-the-art performance on point-cloud-related high-level tasks including category classification. We build upon this work and configure this implementation for amino acid structure recognition.
- Run the training script:
python train.py
- Run the evaluation script after training finished:
python evalutate.py
@article{dgcnn,
title={Dynamic Graph CNN for Learning on Point Clouds},
author={Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon},
journal={arXiv preprint arXiv:1801.07829},
year={2018}
}
Reference: [[Paper]](https://arxiv.org/abs/1801.07829)
MIT License
This code is heavily borrowed from PointNet.