Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
dingchang 21e4b12c32 | 2 years ago | |
---|---|---|
.. | ||
README.md | 2 years ago | |
metafile.yml | 2 years ago | |
pointnet2_msg_16x2_cosine_80e_s3dis_seg-3d-13class.py | 3 years ago | |
pointnet2_msg_16x2_cosine_250e_scannet_seg-3d-20class.py | 3 years ago | |
pointnet2_msg_xyz-only_16x2_cosine_250e_scannet_seg-3d-20class.py | 2 years ago | |
pointnet2_ssg_16x2_cosine_50e_s3dis_seg-3d-13class.py | 3 years ago | |
pointnet2_ssg_16x2_cosine_200e_scannet_seg-3d-20class.py | 3 years ago | |
pointnet2_ssg_xyz-only_16x2_cosine_200e_scannet_seg-3d-20class.py | 2 years ago |
We implement PointNet++ and provide the result and checkpoints on ScanNet and S3DIS datasets.
@inproceedings{qi2017pointnet++,
title={PointNet++ deep hierarchical feature learning on point sets in a metric space},
author={Qi, Charles R and Yi, Li and Su, Hao and Guibas, Leonidas J},
booktitle={Proceedings of the 31st International Conference on Neural Information Processing Systems},
pages={5105--5114},
year={2017}
}
Notice: The original PointNet++ paper used step learning rate schedule. We discovered that cosine schedule achieves much better results and adopt it in our implementations. We also use a larger weight_decay
factor because we find it consistently improves the performance.
Method | Input | Lr schd | Mem (GB) | Inf time (fps) | mIoU (Val set) | mIoU (Test set) | Download |
---|---|---|---|---|---|---|---|
PointNet++ (SSG) | XYZ | cosine 200e | 1.9 | 53.91 | model | log | ||
PointNet++ (SSG) | XYZ+Color | cosine 200e | 1.9 | 54.44 | model | log | ||
PointNet++ (MSG) | XYZ | cosine 250e | 2.4 | 54.26 | model | log | ||
PointNet++ (MSG) | XYZ+Color | cosine 250e | 2.4 | 55.05 | model | log |
Notes:
The original PointNet++ paper conducted experiments on the ScanNet V1 dataset, while later point cloud segmentor papers often used ScanNet V2. Following common practice, we report results on the ScanNet V2 dataset.
Since ScanNet dataset doesn't provide ground-truth labels for the test set, users can only evaluate test set performance by submitting to its online benchmark website. However, users are only allowed to submit once every two weeks. Therefore, we currently report val set mIoU. Test set performance may be added in the future.
To generate submission file for ScanNet online benchmark, you need to modify the ScanNet dataset's config. Change ann_file=data_root + 'scannet_infos_val.pkl'
to ann_file=data_root + 'scannet_infos_test.pkl'
, and then simply run:
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --format-only --options 'txt_prefix=exps/pointnet2_scannet_results'
This will save the prediction results as txt
files in exps/pointnet2_scannet_results/
. Then, go to this folder and zip all files into pn2_scannet.zip
. Now you can submit it to the online benchmark and wait for the test set result. More instructions can be found at their official website.
Method | Split | Lr schd | Mem (GB) | Inf time (fps) | mIoU (Val set) | Download |
---|---|---|---|---|---|---|
PointNet++ (SSG) | Area_5 | cosine 50e | 3.6 | 56.93 | model | log | |
PointNet++ (MSG) | Area_5 | cosine 80e | 3.6 | 58.04 | model | log |
Notes:
Area_5
Split means training the model on Area_1, 2, 3, 4, 6 and testing on Area_5.Since PointNet++ testing adopts sliding patch inference which involves random point sampling, and the test script uses fixed random seeds while the random seeds of validation in training are not fixed, the test results may be slightly different from the results reported above.
No Description
Python C++ Cuda Pickle Text other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》