首页下载资源前端wish20241105

ZIPwish20241105

yyfhq5.53MB需要积分:1

资源文件列表:

Point-PN-main.zip 大约有49个文件
  1. datasets/
  2. datasets/data_mn40.py 3.66KB
  3. datasets/data_pn_mn40.py 3.34KB
  4. datasets/data_pn_scan.py 7.64KB
  5. datasets/data_scan.py 2.07KB
  6. datasets/data_seg.py 4.29KB
  7. LICENSE 1.04KB
  8. logger.py 1.79KB
  9. models/
  10. models/__init__.py 162B
  11. models/model_utils.py 1.74KB
  12. models/point_nn.py 5.91KB
  13. models/point_nn_seg.py 8.07KB
  14. models/point_pn.py 8.83KB
  15. pipeline.png 725.46KB
  16. Point-NN_arxiv.pdf 5.25MB
  17. pointnet2_ops_lib/
  18. pointnet2_ops_lib/MANIFEST.in 29B
  19. pointnet2_ops_lib/pointnet2_ops/
  20. pointnet2_ops_lib/pointnet2_ops/__init__.py 123B
  21. pointnet2_ops_lib/pointnet2_ops/_ext-src/
  22. pointnet2_ops_lib/pointnet2_ops/_ext-src/include/
  23. pointnet2_ops_lib/pointnet2_ops/_ext-src/include/ball_query.h 163B
  24. pointnet2_ops_lib/pointnet2_ops/_ext-src/include/cuda_utils.h 1.27KB
  25. pointnet2_ops_lib/pointnet2_ops/_ext-src/include/group_points.h 183B
  26. pointnet2_ops_lib/pointnet2_ops/_ext-src/include/interpolate.h 386B
  27. pointnet2_ops_lib/pointnet2_ops/_ext-src/include/sampling.h 260B
  28. pointnet2_ops_lib/pointnet2_ops/_ext-src/include/utils.h 983B
  29. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/
  30. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/ball_query.cpp 1.01KB
  31. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/ball_query_gpu.cu 1.74KB
  32. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/bindings.cpp 570B
  33. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/group_points.cpp 1.91KB
  34. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/group_points_gpu.cu 2.82KB
  35. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/interpolate.cpp 3.23KB
  36. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/interpolate_gpu.cu 5.02KB
  37. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/sampling.cpp 2.83KB
  38. pointnet2_ops_lib/pointnet2_ops/_ext-src/src/sampling_gpu.cu 6.85KB
  39. pointnet2_ops_lib/pointnet2_ops/_version.py 22B
  40. pointnet2_ops_lib/pointnet2_ops/pointnet2_modules.py 6.38KB
  41. pointnet2_ops_lib/pointnet2_ops/pointnet2_utils.py 10.15KB
  42. pointnet2_ops_lib/setup.py 1.16KB
  43. README.md 4.82KB
  44. requirements.txt 193B
  45. run_nn_cls.py 4.31KB
  46. run_nn_seg.py 5.4KB
  47. run_pn_mn40.py 10.11KB
  48. run_pn_scan.py 11.14KB
  49. utils.py 12.66KB

资源介绍:

wish20241105
# Parameter is Not All You Need Official implementation of ['Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis'](https://arxiv.org/pdf/2303.08134.pdf). The paper has been accepted by **CVPR 2023** 🔥. [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/parameter-is-not-all-you-need-starting-from/training-free-3d-point-cloud-classification)](https://paperswithcode.com/sota/training-free-3d-point-cloud-classification?p=parameter-is-not-all-you-need-starting-from) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/parameter-is-not-all-you-need-starting-from/training-free-3d-point-cloud-classification-1)](https://paperswithcode.com/sota/training-free-3d-point-cloud-classification-1?p=parameter-is-not-all-you-need-starting-from) [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/parameter-is-not-all-you-need-starting-from/training-free-3d-part-segmentation-on)](https://paperswithcode.com/sota/training-free-3d-part-segmentation-on?p=parameter-is-not-all-you-need-starting-from) ## News * **Seg-NN** has been accepted as ***CVPR 2024 Highlight Paper*** 🔥! * We release [Seg-NN](https://arxiv.org/pdf/2404.04050.pdf) and [code](https://github.com/yangyangyang127/Seg-NN), which adapts Point-NN & Point-PN into 3D scene segmentation tasks 🔥. * For the first time, we conduct 3D analysis entirely requiring $\color{darkorange}{No\ Parameter\ or\ Training\.}$ 💥 * The code of Point-PN has been released 📌. * The code of Point-NN for shape classification and part segmentation has been released. ## Introduction We present a **N**on-parametric **N**etwork for 3D point cloud analysis, **Point-NN**, which consists of purely non-learnable components. Surprisingly, requiring no parameters or training, it performs well on various 3D tasks, and even surpasses existing fully trained models. Starting from this basic non-parametric model, we propose two extensions. First, Point-NN can serve as a base architectural framework to construct **P**arametric **N**etworks, **Point-PN**, which exhibits superior performance with simple linear layers. Second, Point-NN can be regarded as a plug-and-play module to enhance the already trained 3D models during inference by complementary knowledge.
## Requirements ### Installation Create a conda environment and install dependencies: ```bash git clone https://github.com/ZrrSkywalker/Point-NN.git cd Point-NN conda create -n pointnn python=3.7 conda activate pointnn # Install the according versions of torch and torchvision conda install pytorch torchvision cudatoolkit pip install -r requirements.txt pip install pointnet2_ops_lib/. ``` ### Dataset Please download the following datasets: [ModelNet40](https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip), [ScanObjectNN](https://hkust-vgd.ust.hk/scanobjectnn/h5_files.zip), and [ShapeNetPart](https://shapenet.cs.stanford.edu/media/shapenetcore_partanno_segmentation_benchmark_v0_normal.zip). Then, create a `data/` folder and organize the datasets as ``` data/ |–– h5_files/ |–– modelnet40_ply_hdf5_2048/ |–– shapenetcore_partanno_segmentation_benchmark_v0_normal/ ``` ## Point-NN --- Very Quick Implementation 🚀 ### Shape Classification Due to the training-free manner, the preparation and inference of Point-NN only take **2 minutes**. For ModelNet40 dataset, just run: ```bash python run_nn_cls.py --dataset mn40 ``` For ScanObjectNN dataset, just run: ```bash python run_nn_cls.py --dataset scan --split 1 ``` Please indicate the splits at `--split` by `1,2,3` for OBJ-BG, OBJ-ONLY, and PB-T50-RS, respectively. ### Part Segmentation For ShapeNetPart, Point-NN takes **7 minutes** to achieve 71.5% mIOU (70.4% in the paper), just run: ```bash python run_nn_seg.py ``` You can increase the point number `--points` and k-NN neighbors `--k` into `2048` and `128`, which further acheives **74%** with 18 minutes. ## Point-PN ### Shape Classification Point-PN is the parametric version of Point-NN with efficient parameters and simple 3D operators. For ModelNet40 dataset, just run: ```bash python run_pn_mn40.py --msg ``` For ScanObjectNN dataset, just run: ```bash python run_pn_scan.py --split 1 --msg ``` Please indicate the splits at `--split` by `1,2,3` for OBJ-BG, OBJ-ONLY, and PB-T50-RS, respectively. ## Citation ```bash @article{zhang2023parameter, title={Parameter is not all you need: Starting from non-parametric networks for 3d point cloud analysis}, author={Zhang, Renrui and Wang, Liuhui and Wang, Yali and Gao, Peng and Li, Hongsheng and Shi, Jianbo}, journal={arXiv preprint arXiv:2303.08134}, year={2023} } ``` ## Contact If you have any question about this project, please feel free to contact zhangrenrui@pjlab.org.cn.
100+评论
captcha

    相关资源

    1. 钢材表面缺陷检测数据集

      2301_80206469#人工智能ZIP6.54MB4月前
      资源摘要:钢材表面缺陷检测数据集是一个专门针对钢材表面缺陷检测的深度学习训练与测试资源。这个数据集的创建旨在推动钢铁工业中自动化检测技术的发展，提高生产效率和产品质量。它包含了大量经过精心标注的真实钢材图像，用于训练和验证深度学习模型，特别是针对目标检测任务的算法，如YOLO（You Only Look Once）。一、表面缺陷检测的重要性：在钢铁制造过程中，表面缺陷可能会影响材料的性能和寿命，甚至导致结构的失效。因此，及时、准确地检测出这些缺陷至关重要。传统的检测方法依赖于人工视觉检查，成本高且易受主观因素影响。随着机器学习和深度学习技术的进步，自动化检测已成为解决这一问题的有效途径。二、深度学习在表面缺陷检测中的应用：1. YOLO（You Only Look Once）：YOLO是一种实时的目标检测系统，以其快速的检测速度和相对较高的准确性而受到广泛关注。在NEU-DET数据集中，YOLO可以被训练来识别并定位钢材表面的缺陷，如裂纹、锈斑、凹痕等。2. 特征提取：深度学习模型，如卷积神经网络（CNN），能自动从图像中学习高级特征，这对于识别复杂的表面缺

    2. 期中复习大礼包.zip

      2401_87724454#行业研究ZIP17.32MB4月前
      资源摘要:期中复习大礼包.zip

    3. 设备配件管理和设备检修系统 SSM毕业设计 附带论文.zip

      zhang_hao_chao#行业研究ZIP11.69MB4月前
      资源摘要:设备配件管理和设备检修系统 SSM毕业设计 附带论文启动教程:https://www.bilibili.com/video/BV1GK1iYyE2B

    4. 程序设计课程可视化教学系统 SSM毕业设计 附带论文.zip

      zhang_hao_chao#行业研究ZIP12.47MB4月前
      资源摘要:程序设计课程可视化教学系统 SSM毕业设计 附带论文启动教程:https://www.bilibili.com/video/BV1GK1iYyE2B

    5. 使用C#进行Yolov5模型的训练以及推理

      qq_30270773#人工智能ZIP6.69MB4月前
      资源摘要:使用纯C#语言训练Yolov5模型，并且使用自己训练的模型进行推理。

    6. 校园家教兼职信息交流平台 SSM毕业设计 附带论文.zip

      zhang_hao_chao#行业研究ZIP19.08MB4月前
      资源摘要:校园家教兼职信息交流平台 SSM毕业设计 附带论文启动教程:https://www.bilibili.com/video/BV1GK1iYyE2B

    7. 校园停车场管理系统 SSM毕业设计 附带论文.zip

      zhang_hao_chao#行业研究ZIP13.56MB4月前
      资源摘要:校园停车场管理系统 SSM毕业设计 附带论文启动教程:https://www.bilibili.com/video/BV1GK1iYyE2B

    8. 摊位管理系统 SSM毕业设计 附带论文.zip

      zhang_hao_chao#行业研究ZIP48MB4月前
      资源摘要:摊位管理系统 SSM毕业设计 附带论文启动教程:https://www.bilibili.com/video/BV1GK1iYyE2B
    站长QQ:九六九五七三七