this is a program with pointnet and ccf2018 dataset, so please read the author papers of pointnet, and you should konw the dataset of ccf2018(3D PCL). And following will be difference
This repo is implementation for PointNet(https://arxiv.org/abs/1612.00593) in pytorch. The model is in pointnet/model.py.
It is tested with pytorch-1.0.
git clone https://github.com/fxia22/pointnet.pytorch
cd pointnet.pytorch
pip install -e .
Download and build visualization tool
cd script
bash build.sh #build C++ code for visualization
bash download.sh #download dataset
Training
cd utils
python train_classification.py --dataset <dataset path> --nepoch=<number epochs> --dataset_type <modelnet40 | shapenet>
python train_segmentation.py --dataset <dataset path> --nepoch=<number epochs>
Use --feature_transform to use feature transform.
On ModelNet40:
| Overall Acc | |
|---|---|
| Original implementation | 89.2 |
| this implementation(w/o feature transform) | 86.4 |
| this implementation(w/ feature transform) | 87.0 |
| Overall Acc | |
|---|---|
| Original implementation | N/A |
| this implementation(w/o feature transform) | 98.1 |
| this implementation(w/ feature transform) | 97.7 |
Segmentation on A subset of shapenet.
| Class(mIOU) | Airplane | Bag | Cap | Car | Chair | Earphone | Guitar | Knife | Lamp | Laptop | Motorbike | Mug | Pistol | Rocket | Skateboard | Table |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Original implementation | 83.4 | 78.7 | 82.5 | 74.9 | 89.6 | 73.0 | 91.5 | 85.9 | 80.8 | 95.3 | 65.2 | 93.0 | 81.2 | 57.9 | 72.8 | 80.6 |
| this implementation(w/o feature transform) | 73.5 | 71.3 | 64.3 | 61.1 | 87.2 | 69.5 | 86.1 | 81.6 | 77.4 | 92.7 | 41.3 | 86.5 | 78.2 | 41.2 | 61.0 | 81.1 |
| this implementation(w/ feature transform) | 87.6 | 81.0 |
Note that this implementation trains each class separately, so classes with fewer data will have slightly lower performance than reference implementation.
Sample segmentation result:
