guochengqian/PointNeXt

How to visualize Scannet dataset?

Opened this issue · 5 comments

Qiyuan-Liu commented

Hi PointNeXt team,

Is there a way to generate the predicted ScanNet point cloud and visualize them?

Looking forward to your reply. Hope you have a great one.

Best regards,

Liu

HJ-Xu commented

Hi Liu

Has your issue been resolved? I would like to know how to visualize the Shapenetpart and S3DIS datasets. Do you have any suggestions on how to implement this?

Looking forward to your reply.

Best regards,

Xu

  • 👍1
Ahren606 commented

You need to create a cmap for color mapping in /openpoints/dataset/scannetv2.py by following the example of the s3dis file. Then, when running the test command, add visualize=True. Since the test data does not have labels, only generate .obj files for the input and the PointNeXt-XL prediction results. If ground truth visualization is needed, replace the data in the test folder with the data from the val folder and change no_label=True to False in the test command line,And change None to data[2] inhttps://github.com/guochengqian/PointNeXt/blob/8a0ec91de5329b3b3e346422fa43a51ba24fd450/examples/segmentation/main.py#L76.

YOOOOOL commented

You need to create a cmap for color mapping in /openpoints/dataset/scannetv2.py by following the example of the s3dis file. Then, when running the test command, add visualize=True. Since the test data does not have labels, only generate .obj files for the input and the PointNeXt-XL prediction results. If ground truth visualization is needed, replace the data in the test folder with the data from the val folder and change no_label=True to False in the test command line,And change None to data[2] inhttps://github.com/guochengqian/PointNeXt/blob/8a0ec91de5329b3b3e346422fa43a51ba24fd450/examples/segmentation/main.py#L76.
Thank you for your sharing, but when I followed your steps to visualize the ground truth, I encountered the following problems. Can you give me some advice?
File "examples/segmentation/main.py", line 627, in test
gt = cfg.cmap[gt, :] if gt is not None else None
IndexError: index 20 is out of bounds for axis 0 with size 20

Ahren606 commented

您需要按照 s3dis 文件的示例在 /openpoints/dataset/scannetv2.py 中创建用于颜色映射的 cmap。然后，在运行测试命令时，添加 visualize=True。由于测试数据没有标签，因此只为输入和 PointNeXt-XL 预测结果生成 .obj 文件。如果需要真值可视化，请将 test 文件夹中的数据替换为 val 文件夹中的数据，并在测试命令行中将 no_label=True 更改为 False，并将 None 更改为 data[2] inhttps://github.com/guochengqian/PointNeXt/blob/8a0ec91de5329b3b3e346422fa43a51ba24fd450/examples/segmentation/main.py#L76。感谢您的分享，但是当我按照您的步骤可视化 Ground Truth 时，我遇到了以下问题。您能给我一些建议吗？文件 “examples/segmentation/main.py”，第 627 行，在测试 gt = cfg.cmap[gt， ：] 中，如果 gt 不是 None None IndexError： index 20 is outs of bounds for axis 0 size 20

There may have been an error while creating the cmap, possibly exceeding the number of categories in the dataset. Check the cmap you created.

YOOOOOL commented

您需要按照 s3dis 文件的示例在 /openpoints/dataset/scannetv2.py 中创建用于颜色映射的 cmap。然后，在运行测试命令时，添加 visualize=True。由于测试数据没有标签，因此只为输入和 PointNeXt-XL 预测结果生成 .obj 文件。如果需要真值可视化，请将 test 文件夹中的数据替换为 val 文件夹中的数据，并在测试命令行中将 no_label=True 更改为 False，并将 None 更改为 data[2] inhttps://github.com/guochengqian/PointNeXt/blob/8a0ec91de5329b3b3e346422fa43a51ba24fd450/examples/segmentation/main.py#L76。感谢您的分享，但是当我按照您的步骤可视化 Ground Truth 时，我遇到了以下问题。您能给我一些建议吗？文件 “examples/segmentation/main.py”，第 627 行，在测试 gt = cfg.cmap[gt， ：] 中，如果 gt 不是 None None IndexError： index 20 is outs of bounds for axis 0 size 20

There may have been an error while creating the cmap, possibly exceeding the number of categories in the dataset. Check the cmap you created.
Thank you very much for your help, the project can run normally