This repository contains the implementation of RandLA-Net (CVPR 2020 Oral) in PyTorch.

• We only support SemanticKITTI dataset now. (Welcome everyone to develop together and raise PR)
• Our model is almost as good as the original implementation. (Validation set : Our 52.9% mIoU vs original 53.1%)
• We place our pretrain-model in pretrain_model/checkpoint.tar directory.

Results on Validation Set (seq 08)

• Compare with original implementation

• Per class mIoU

0. Click this webpage and use conda to install pytorch>=1.4 (Be aware of the cuda version when installation)

1. Install python packages

pip install -r requirements.txt

2. Compile C++ Wrappers

bash compile_op.sh

Download the Semantic KITTI dataset, and preprocess the data:

python data_prepare_semantickitti.py

Note:

• Please change the dataset path in the data_prepare_semantickitti.py with your own path.
• Data preprocessing code will convert the label to 0-19 index

1. Training

python3 train_SemanticKITTI.py <args>

2. Testing

python3 test_SemanticKITTI.py <args>

Note: if the flag --index_to_label is set, output predictions will be ".label" files (label figure) which can be visualized; Otherwise, they will be ".npy" (0-19 index) files which is used to evaluated afterward.

1. Visualization

python3 visualize_SemanticKITTI.py <args>

2. Evaluation

• Example Evaluation code

python3 evaluate_SemanticKITTI.py --dataset /tmp2/tsunghan/PCL_Seg_data/sequences_0.06/ \
    --predictions runs/supervised/predictions/ --sequences 8

• Original Tensorflow implementation link
• Our network & config codes are modified from RandLA-Net PyTorch
• Our evaluation & visualization codes are modified from SemanticKITTI API