# Module: tfg.nn.layer.pointnet

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/graphics/blob/master/tensorflow_graphics/nn/layer/pointnet.py) |

Implementation of the PointNet networks.

@inproceedings{qi2017pointnet,
title={Pointnet: Deep learning on point sets
for3d classification and segmentation},
author={Qi, Charles R and Su, Hao and Mo, Kaichun and Guibas, Leonidas J},
booktitle={Proceedings of the IEEE conference on computer vision and pattern
recognition},
pages={652--660},
year={2017} }

> [!NOTE]
> **Note:** scheduling of batchnorm momentum currently not available in keras. However experimentally, using the batch norm from Keras resulted in better test accuracy (+1.5%) than the author's [custom batch norm
> version](https://github.com/charlesq34/pointnet/blob/master/utils/tf_util.py) even when coupled with batchnorm momentum decay. Further, note the author's version is actually performing a "global normalization", as mentioned in the [tf.nn.moments documentation](https://www.tensorflow.org/api_docs/python/tf/nn/moments).

This shorthand notation is used throughout this module:
`B`: Number of elements in a batch.
`N`: The number of points in the point set.
`D`: Number of dimensions (e.g. 2 for 2D, 3 for 3D).
`C`: The number of feature channels.

## Classes

[`class ClassificationHead`](https://www.tensorflow.org/graphics/api_docs/python/tfg/nn/layer/pointnet/ClassificationHead): The PointNet classification head.

[`class PointNetConv2Layer`](https://www.tensorflow.org/graphics/api_docs/python/tfg/nn/layer/pointnet/PointNetConv2Layer): The 2D convolution layer used by the feature encoder in PointNet.

[`class PointNetDenseLayer`](https://www.tensorflow.org/graphics/api_docs/python/tfg/nn/layer/pointnet/PointNetDenseLayer): The fully connected layer used by the classification head in pointnet.

[`class PointNetVanillaClassifier`](https://www.tensorflow.org/graphics/api_docs/python/tfg/nn/layer/pointnet/PointNetVanillaClassifier): The PointNet 'Vanilla' classifier (i.e. without spatial transformer).

[`class VanillaEncoder`](https://www.tensorflow.org/graphics/api_docs/python/tfg/nn/layer/pointnet/VanillaEncoder): The Vanilla PointNet feature encoder.