下载资源人工智能资源详情
SoftGroup.zip
大小:2.73MB
价格:42积分
下载量:0
评分:
5.0
上传者:u012901740
更新日期:2025-09-22

点云实例分割-Softgroup-训练自己数据集程序

资源文件列表(大概)

文件名
大小
SoftGroup/
-
SoftGroup/.flake8
148B
SoftGroup/.gitignore
1.01KB
SoftGroup/.pre-commit-config.yaml
954B
SoftGroup/configs/
-
SoftGroup/configs/softgroup/
-
SoftGroup/configs/softgroup/softgroup_kitti.yaml
1.61KB
SoftGroup/configs/softgroup/softgroup_kitti_backbone.yaml
1.56KB
SoftGroup/configs/softgroup/softgroup_s3dis.yaml
1.54KB
SoftGroup/configs/softgroup/softgroup_s3dis_backbone_fold5.yaml
1.52KB
SoftGroup/configs/softgroup/softgroup_s3dis_fold5.yaml
1.66KB
SoftGroup/configs/softgroup/softgroup_scannet.yaml
1.68KB
SoftGroup/configs/softgroup/softgroup_scannet_backbone.yaml
1.67KB
SoftGroup/configs/softgroup/softgroup_soybean.yaml
1.35KB
SoftGroup/configs/softgroup/softgroup_stpls3d.yaml
1.71KB
SoftGroup/configs/softgroup/softgroup_stpls3d_backbone.yaml
1.58KB
SoftGroup/configs/softgroup++/
-
SoftGroup/configs/softgroup++/softgroup++_s3dis_backbone_fold1.yaml
1.53KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_backbone_fold2.yaml
1.53KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_backbone_fold3.yaml
1.53KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_backbone_fold4.yaml
1.53KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_backbone_fold5.yaml
1.53KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_backbone_fold6.yaml
1.53KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_fold1.yaml
1.73KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_fold2.yaml
1.73KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_fold3.yaml
1.73KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_fold4.yaml
1.73KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_fold5.yaml
1.73KB
SoftGroup/configs/softgroup++/softgroup++_s3dis_fold6.yaml
1.73KB
SoftGroup/configs/softgroup++/softgroup++_scannet.yaml
1.75KB
SoftGroup/configs/softgroup++/softgroup++_stpls3d.yaml
1.81KB
SoftGroup/configs/softgroup++/softgroup++_stpls3d_backbone.yaml
1.56KB
SoftGroup/dataset/
-
SoftGroup/dataset/kitti/
-
SoftGroup/dataset/kitti/semantic-kitti.yaml
5.41KB
SoftGroup/dataset/README.md
2.11KB
SoftGroup/dataset/s3dis/
-
SoftGroup/dataset/s3dis/downsample.py
2.5KB
SoftGroup/dataset/s3dis/prepare_data.sh
95B
SoftGroup/dataset/s3dis/prepare_data_inst.py
5.57KB
SoftGroup/dataset/s3dis/prepare_data_inst_gttxt.py
2.14KB
SoftGroup/dataset/scannetv2/
-
SoftGroup/dataset/scannetv2/prepare_data.sh
241B
SoftGroup/dataset/scannetv2/prepare_data_inst.py
3.68KB
SoftGroup/dataset/scannetv2/prepare_data_inst_gttxt.py
1.63KB
SoftGroup/dataset/scannetv2/scannetv2_test.txt
1.27KB
SoftGroup/dataset/scannetv2/scannetv2_train.txt
15.25KB
SoftGroup/dataset/scannetv2/scannetv2_val.txt
3.96KB
SoftGroup/dataset/scannetv2/scannet_util.py
1018B
SoftGroup/dataset/scannetv2/split_data.py
1.3KB
SoftGroup/dataset/stpls3d/
-
SoftGroup/dataset/stpls3d/prepare_data.sh
78B
SoftGroup/dataset/stpls3d/prepare_data_inst_instance_stpls3d.py
7.4KB
SoftGroup/dataset/stpls3d/prepare_data_statistic_stpls3d.py
2.92KB
SoftGroup/docs/
-
SoftGroup/docs/architecture.png
82.95KB
SoftGroup/docs/config_explanation.md
4.48KB
SoftGroup/docs/custom_dataset.md
2.32KB
SoftGroup/docs/installation.md
727B
SoftGroup/docs/leaderboard.png
251.19KB
SoftGroup/docs/train_logs/
-
SoftGroup/docs/train_logs/softgroup_s3dis_fold5_20220602_075350.log
131.47KB
SoftGroup/docs/train_logs/softgroup_scannet_20220602_120228.log
945.36KB
SoftGroup/docs/visualization.md
1.29KB
SoftGroup/LICENSE
1.03KB
SoftGroup/README.md
8.62KB
SoftGroup/requirements.txt
81B
SoftGroup/setup.cfg
405B
SoftGroup/setup.py
896B
SoftGroup/softgroup/
-
SoftGroup/softgroup/data/
-
SoftGroup/softgroup/data/custom.py
10.76KB
SoftGroup/softgroup/data/kitti.py
5.06KB
SoftGroup/softgroup/data/s3dis.py
4.51KB
SoftGroup/softgroup/data/scannetv2.py
1.14KB
SoftGroup/softgroup/data/soybean.py
10.79KB
SoftGroup/softgroup/data/stpls3d.py
739B
SoftGroup/softgroup/data/__init__.py
1.77KB
SoftGroup/softgroup/data/__pycache__/
-
SoftGroup/softgroup/data/__pycache__/custom.cpython-38.pyc
8.63KB
SoftGroup/softgroup/data/__pycache__/kitti.cpython-38.pyc
4.09KB
SoftGroup/softgroup/data/__pycache__/s3dis.cpython-38.pyc
3.59KB
SoftGroup/softgroup/data/__pycache__/scannetv2.cpython-38.pyc
1.48KB
SoftGroup/softgroup/data/__pycache__/soybean.cpython-38.pyc
8.69KB
SoftGroup/softgroup/data/__pycache__/stpls3d.cpython-38.pyc
1.01KB
SoftGroup/softgroup/data/__pycache__/__init__.cpython-38.pyc
1.35KB
SoftGroup/softgroup/evaluation/
-
SoftGroup/softgroup/evaluation/instance_eval.py
18.53KB
SoftGroup/softgroup/evaluation/instance_eval_util.py
5.21KB
SoftGroup/softgroup/evaluation/panoptic_eval.py
10.19KB
SoftGroup/softgroup/evaluation/point_wise_eval.py
1.58KB
SoftGroup/softgroup/evaluation/__init__.py
269B
SoftGroup/softgroup/evaluation/__pycache__/
-
SoftGroup/softgroup/evaluation/__pycache__/instance_eval.cpython-38.pyc
9.01KB
SoftGroup/softgroup/evaluation/__pycache__/instance_eval_util.cpython-38.pyc
5.14KB
SoftGroup/softgroup/evaluation/__pycache__/panoptic_eval.cpython-38.pyc
6.22KB
SoftGroup/softgroup/evaluation/__pycache__/point_wise_eval.cpython-38.pyc
1.66KB
SoftGroup/softgroup/evaluation/__pycache__/__init__.cpython-38.pyc
405B
SoftGroup/softgroup/model/
-
SoftGroup/softgroup/model/blocks.py
5.06KB
SoftGroup/softgroup/model/softgroup.py
33.36KB
SoftGroup/softgroup/model/__init__.py
58B
SoftGroup/softgroup/model/__pycache__/
-
SoftGroup/softgroup/model/__pycache__/blocks.cpython-38.pyc
4.1KB
SoftGroup/softgroup/model/__pycache__/softgroup.cpython-38.pyc
19.39KB
SoftGroup/softgroup/model/__pycache__/__init__.cpython-38.pyc
199B
SoftGroup/softgroup/ops/
-
SoftGroup/softgroup/ops/clang_format.sh
120B
SoftGroup/softgroup/ops/functions.py
13.08KB
SoftGroup/softgroup/ops/ops.cpython-38-x86_64-linux-gnu.so
7.6MB
SoftGroup/softgroup/ops/setup.py
429B
SoftGroup/softgroup/ops/src/
-
SoftGroup/softgroup/ops/src/bfs_cluster/
-
SoftGroup/softgroup/ops/src/bfs_cluster/bfs_cluster.cpp
4.51KB
SoftGroup/softgroup/ops/src/bfs_cluster/bfs_cluster.cu
2.71KB
SoftGroup/softgroup/ops/src/bfs_cluster/bfs_cluster.h
1.08KB
SoftGroup/softgroup/ops/src/cal_iou_and_masklabel/
-
SoftGroup/softgroup/ops/src/cal_iou_and_masklabel/cal_iou_and_masklabel.cpp
4.15KB
SoftGroup/softgroup/ops/src/cal_iou_and_masklabel/cal_iou_and_masklabel.cu
6.8KB
SoftGroup/softgroup/ops/src/cal_iou_and_masklabel/cal_iou_and_masklabel.h
2.22KB
SoftGroup/softgroup/ops/src/cuda.cu
781B
SoftGroup/softgroup/ops/src/cuda_utils.h
574B
SoftGroup/softgroup/ops/src/datatype/
-
SoftGroup/softgroup/ops/src/datatype/datatype.cpp
436B
SoftGroup/softgroup/ops/src/datatype/datatype.h
1.22KB
SoftGroup/softgroup/ops/src/octree_ball_query/
-
SoftGroup/softgroup/ops/src/octree_ball_query/octree_ball_query.cpp
5.54KB
SoftGroup/softgroup/ops/src/octree_ball_query/octree_ball_query.cu
5.17KB
SoftGroup/softgroup/ops/src/octree_ball_query/octree_ball_query.h
1.93KB
SoftGroup/softgroup/ops/src/roipool/
-
SoftGroup/softgroup/ops/src/roipool/roipool.cpp
1.03KB
SoftGroup/softgroup/ops/src/roipool/roipool.cu
2.48KB
SoftGroup/softgroup/ops/src/roipool/roipool.h
895B
SoftGroup/softgroup/ops/src/sec_mean/
-
SoftGroup/softgroup/ops/src/sec_mean/sec_mean.cpp
1.03KB
SoftGroup/softgroup/ops/src/sec_mean/sec_mean.cu
2.88KB
SoftGroup/softgroup/ops/src/sec_mean/sec_mean.h
864B
SoftGroup/softgroup/ops/src/softgroup_api.cpp
1.1KB
SoftGroup/softgroup/ops/src/softgroup_ops.cpp
1.48KB
SoftGroup/softgroup/ops/src/softgroup_ops.h
1.09KB
SoftGroup/softgroup/ops/src/voxelize/
-
SoftGroup/softgroup/ops/src/voxelize/voxelize.cpp
6.07KB
SoftGroup/softgroup/ops/src/voxelize/voxelize.cu
2.29KB
SoftGroup/softgroup/ops/src/voxelize/voxelize.h
2.05KB
SoftGroup/softgroup/ops/__init__.py
25B
SoftGroup/softgroup/ops/__pycache__/
-
SoftGroup/softgroup/ops/__pycache__/functions.cpython-38.pyc
10.81KB
SoftGroup/softgroup/ops/__pycache__/__init__.cpython-38.pyc
158B
SoftGroup/softgroup/util/
-
SoftGroup/softgroup/util/dist.py
3.59KB
SoftGroup/softgroup/util/fp16.py
2.65KB
SoftGroup/softgroup/util/logger.py
1.11KB
SoftGroup/softgroup/util/optim.py
296B
SoftGroup/softgroup/util/rle.py
1.01KB
SoftGroup/softgroup/util/utils.py
5KB
SoftGroup/softgroup/util/__init__.py
299B
SoftGroup/softgroup/util/__pycache__/
-
SoftGroup/softgroup/util/__pycache__/dist.cpython-38.pyc
3.15KB
SoftGroup/softgroup/util/__pycache__/fp16.cpython-38.pyc
2.14KB
SoftGroup/softgroup/util/__pycache__/logger.cpython-38.pyc
1.38KB
SoftGroup/softgroup/util/__pycache__/optim.cpython-38.pyc
587B
SoftGroup/softgroup/util/__pycache__/rle.cpython-38.pyc
1.45KB
SoftGroup/softgroup/util/__pycache__/utils.cpython-38.pyc
5.11KB
SoftGroup/softgroup/util/__pycache__/__init__.cpython-38.pyc
516B
SoftGroup/tools/
-
SoftGroup/tools/convert_checkpoint.py
973B
SoftGroup/tools/dist_test.sh
204B
SoftGroup/tools/dist_train.sh
176B
SoftGroup/tools/eval_det.py
10.97KB
SoftGroup/tools/test.py
8.31KB
SoftGroup/tools/train.py
8.81KB
SoftGroup/tools/visualization.py
10.23KB

资源内容介绍

根据官方代码修改可以训练自己的数据程序项目
# SoftGroup[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/softgroup-for-3d-instance-segmentation-on/3d-instance-segmentation-on-scannetv2)](https://paperswithcode.com/sota/3d-instance-segmentation-on-scannetv2?p=softgroup-for-3d-instance-segmentation-on) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/softgroup-for-3d-instance-segmentation-on/3d-instance-segmentation-on-s3dis)](https://paperswithcode.com/sota/3d-instance-segmentation-on-s3dis?p=softgroup-for-3d-instance-segmentation-on) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/softgroup-for-3d-instance-segmentation-on/3d-object-detection-on-scannetv2)](https://paperswithcode.com/sota/3d-object-detection-on-scannetv2?p=softgroup-for-3d-instance-segmentation-on)![Architecture](./docs/architecture.png)We provide code for reproducing results of two papers [**SoftGroup for 3D Instance Segmentation on Point Clouds**](https://arxiv.org/abs/2203.01509)\Thang Vu, Kookhoi Kim, Tung M. Luu, Thanh Nguyen, and Chang D. Yoo.\**CVPR 2022 (Oral)**.[**Scalable SoftGroup for 3D Instance Segmentation on Point Clouds**](https://arxiv.org/abs/2209.08263)\Thang Vu, Kookhoi Kim, Tung M. Luu, Thanh Nguyen, Junyeong Kim, and Chang D. Yoo.\**TPAMI 2023 (accepted)**.## Update- 25/Nov/2022: Support [SoftGroup++](https://arxiv.org/abs/2209.08263).- 12/Sep/2022: Support panoptic segmentation on SemanticKITTI dataset.- 28/Jun/2022: Support STPLS3D dataset. Add custom dataset guideline.- 16/Apr/2022: The code base is refactored. Coding is more extendable, readable, and consistent. The following features are supported: - Support up-to-date pytorch 1.11 and spconv 2.1. - Support distributed and mix precision training. Training time on ScanNet v2 (on 4GPUs) reduces from 4 day to 10 hours. - Faster inference speed, which requires only 288 ms per ScanNet scan on single Titan X.## IntroductionExisting state-of-the-art 3D instance segmentation methods perform semantic segmentation followed by grouping. The hard predictions are made when performing semantic segmentation such that each point is associated with a single class. However, the errors stemming from hard decision propagate into grouping that results in (1) low overlaps between the predicted instance with the ground truth and (2) substantial false positives. To address the aforementioned problems, this paper proposes a 3D instance segmentation method referred to as SoftGroup by performing bottom-up soft grouping followed by top-down refinement. SoftGroup allows each point to be associated with multiple classes to mitigate the problems stemming from semantic prediction errors and suppresses false positive instances by learning to categorize them as background. Experimental results on different datasets and multiple evaluation metrics demonstrate the efficacy of SoftGroup. Its performance surpasses the strongest prior method by a significant margin of +6.2% on the ScanNet v2 hidden test set and +6.8% on S3DIS Area 5 of AP_50.![Learderboard](./docs/leaderboard.png)## Feature* State of the art performance on the [ScanNet benchmark](http://kaldir.vc.in.tum.de/scannet_benchmark/semantic_instance_3d) and S3DIS dataset (3/Mar/2022).* High speed of 345 ms per scan on ScanNet dataset, which is comparable with the existing fastest methods ([HAIS](https://github.com/hustvl/HAIS)). Our refactored implementation (this code) further reduce the inference time to 288 ms per scan.* Support multiple datasets: ScanNet, S3DIS, STPLS3D, SemanticKITTI.## InstallationPlease refer to [installation guide](docs/installation.md).## Data PreparationPlease refer to [data preparation](dataset/README.md).## Pretrained models### Instance segmentation| Dataset | Model | AP | AP_50 | AP_25 | Download ||:----------:|:-----------:|:----:|:-----:|:-----:|:-------------------------------------------------------------------------------------------:|| S3DIS | SoftGroup | 51.4 | 66.5 | 75.4 | [model](https://drive.google.com/file/d/1-f7I6-eIma4OilBON928N6mVcYbhiUFP/view?usp=sharing) || S3DIS | SoftGroup++ | 50.9 | 67.8 | 76.0 | [model](https://drive.google.com/file/d/1OLbC8lmWkAQbqYAjiFj84egLQmJr-PmQ/view?usp=sharing) || ScanNet v2 | SoftGroup | 45.8 | 67.4 | 79.1 | [model](https://drive.google.com/file/d/1XUNRfred9QAEUY__VdmSgZxGQ7peG5ms/view?usp=sharing) || ScanNet v2 | SoftGroup++ | 45.9 | 67.9 | 79.4 | above || STPLS3D | SoftGroup | 47.3 | 63.1 | 71.4 | [model](https://drive.google.com/file/d/1xCkKLTCYtQmSjXYH_sSg21M_6dcAskd8/view?usp=sharing) || STPLS3D | SoftGroup++ | 46.5 | 62.9 | 71.8 | above |> **_NOTE:_** SoftGroup and SoftGroup++ use can use same trained model for inference on ScanNet v2 and STPLS3D.### Panoptic segmentation| Dataset | PQ | Config | Model ||:-------------:|:----:|:------:|:-----:|| SemanticKITTI | 60.2 | [config](https://github.com/thangvubk/SoftGroup/blob/main/configs/softgroup_kitti.yaml) | [model](https://drive.google.com/file/d/10Ln-xLfl8Z3DX3G3lnO_RruJtYUYDfI7/view?usp=sharing) |## TrainingWe use the checkpoint of [HAIS](https://github.com/hustvl/HAIS) as pretrained backbone. **We have already converted the checkpoint to work on ``spconv2.x``**. Download the pretrained HAIS-spconv2 model and put it in ``SoftGroup/`` directory.Converted hais checkpoint: [model](https://drive.google.com/file/d/1FABsCUnxfO_VlItAzDYAwurdfcdK-scs/view?usp=sharing)Noted that for fair comparison with implementation in STPLS3D paper, we train SoftGroup on this dataset from scratch without pretrained backbone.### Training S3DIS datasetThe default configs suppose training on 4 GPU. If you use smaller number of GPUs, you should reduce the learning rate linearly. First, finetune the pretrained HAIS point-wise prediction network (backbone) on S3DIS.```./tools/dist_train.sh configs/softgroup_s3dis_backbone_fold5.yaml 4```Then, train model from frozen backbone.```./tools/dist_train.sh configs/softgroup_s3dis_fold5.yaml 4```### Training ScanNet V2 datasetTraining on ScanNet doesnot require finetuning the backbone. Just freeze pretrained backbone and train the model.```./tools/dist_train.sh configs/softgroup_scannet.yaml 4```### Training STPLS3D dataset```./tools/dist_train.sh configs/softgroup_stpls3d_backbone.yaml 4./tools/dist_train.sh configs/softgroup_stpls3d.yaml 4```## Inference```./tools/dist_test.sh $CONFIG_FILE $CHECKPOINT $NUM_GPU```### Inference without labelFor example, on scannet test split, just change [``prefix``](https://github.com/thangvubk/SoftGroup/blob/cf88d9be41ae83a70f9100856a3ca15ee4ddcee9/configs/softgroup_scannet.yaml#L49) to ``test`` and [``with_label``](https://github.com/thangvubk/SoftGroup/blob/cf88d9be41ae83a70f9100856a3ca15ee4ddcee9/configs/softgroup_scannet.yaml#L52) to ``False`` before running inference. ### Bounding box evaluation of ScanNet V2 dataset.We provide script to evaluate detection performance on axis-aligned boxes from predicted/ground-truth instance.- Step 1: Change ``save_instance`` to ``True`` in [config file](https://github.com/thangvubk/SoftGroup/blob/99ffb9756e553e0edfb2c43e2ab6a6f646892bb5/config/softgroup_default_scannet.yaml#L72).- Step 2: Run evaluation code.```CUDA_VISIBLE_DEVICES=0 python test.py --config config/softgroup_default_scannet.yaml --pretrain $PATH_TO_PRETRAIN_MODEL$```- Step 3: Evaluate detection performance.```python eval_det.py```## VisualizationPlease refer to [visualization guide](docs/visualization.md) for visualizing ScanNet and S3DIS results.## Custom datasetPlease refer to [custom dataset guide](docs/custom_dataset.md).## CitationIf you find our work helpful for your research. Please consider citing our paper.```@inproceedings{vu2022softgroup, title={SoftGroup for 3D Instance Seg

用户评论 (0)

发表评论

captcha

相关资源

C#编写的一款读取xml文件的mapping图软件 可以自由定位位置，统计数量，蛇形走位 主要用在晶圆图谱识别

C#编写的一款读取xml文件的mapping图软件。可以自由定位位置，统计数量，蛇形走位。主要用在晶圆图谱识别。

293.89KB24积分

stm32步进电机加减速代码 stm32f103stm32步进电机S型加减速程序源码与详细分析，资料为算法实现以及算法的相关

stm32步进电机加减速代码 stm32f103stm32步进电机S型加减速程序源码与详细分析，资料为算法实现以及算法的相关讲解，例程中有stm32f103步进电机S型加减速的完整工程代码，对步进电机s型加减速控制很有帮助。

304.95KB50积分

stm32步进电机S型加减速程序源码与详细分析，

stm32步进电机S型加减速程序源码与详细分析，

146.86KB18积分

《基于改进粒子群算法的混合储能系统容量优化》完全复现matlab 以全生命周期费用最低为目标函数，负荷缺电率作为风光互补发电

《基于改进粒子群算法的混合储能系统容量优化》完全复现matlab。以全生命周期费用最低为目标函数，负荷缺电率作为风光互补发电系统的运行指标，得到蓄电池储能和超级电容个数，缺电率和系统最小费用。粒子群算法：权重改进、对称加速因子、不对称加速因子三种情况的优化结果和迭代曲线。另包含2020年最新提出的阿基米德优化算法AOA和麻雀搜索算法SSA对该lunwen的实现。（该算法收敛速度快，不存在pso的早熟收敛）

681.77KB10积分