want to test my pointcloud, But i do not know how to prepare data for input.

I, FN, B，VC ??? what means this file .txt? .ply file can get these data??

thanks

Hello,

I tried using your provided ABC pre-trained model to test your ABC data. The results are bad, I think that you maybe provide the wrong pre-trained model.

It's normal that after unzipping the 'abc.pth' file, there is a ' scene.pth' file in the checkpoints folder?

Thanks in advance. Best. Mulin

There is a problem about mismatched parameters when executing sh scripts/test_scene.sh: I tried solving it by the method found on the Internet that let me ignore the weight and bias using the following code:

checkpoint.pop("linear_semantics.bias") checkpoint.pop("linear_semantics.weight")

But then I encountered another problem raising an IndexError: How can I handle this? Or if there is another way for the mismatched parameters?

Dear Jingwei,

Thanks for releasing the code. I tried to evaluate the ABC dataset. But I got errors shown in below:

> /home/ubuntu/primitivenet/PrimitiveNet/src/util/config.py:19: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
>   config = yaml.load(f)
> [2021-10-19 15:03:01,872  INFO  log.py  line 40  8783]  ************************ Start Logging ************************
> [2021-10-19 15:03:01,967  INFO  test_boundary.py  line 190  8783]  => creating model ...
> [2021-10-19 15:03:02,059  INFO  test_boundary.py  line 195  8783]  cuda available: True
> [2021-10-19 15:03:04,608  INFO  utils.py  line 61  8783]  Restore from ../checkpoints/abc.pth
> Traceback (most recent call last):
>   File "test_boundary.py", line 202, in <module>
>     start_epoch = utils.checkpoint_restore(model, cfg.exp_path, cfg.config.split('/')[-1][:-5], use_cuda, 0, False, cfg.pretrain)
>   File "/home/ubuntu/primitivenet/PrimitiveNet/src/util/utils.py", line 62, in checkpoint_restore
>     checkpoint = torch.load(f)
>   File "/usr/local/lib/python3.8/dist-packages/torch/serialization.py", line 601, in load
>     if _is_torchscript_zip(opened_zipfile):
>   File "/usr/local/lib/python3.8/dist-packages/torch/serialization.py", line 890, in _is_torchscript_zip
>     return 'constants.pkl' in zip_file.get_all_records()
> RuntimeError: [enforce fail at inline_container.cc:230] . file in archive is not in a subdirectory archive/: checkpoints/scene.pth
> /usr/lib/python3/dist-packages/numpy/core/fromnumeric.py:3256: RuntimeWarning: Mean of empty slice.
>   return _methods._mean(a, axis=axis, dtype=dtype,
> /usr/lib/python3/dist-packages/numpy/core/_methods.py:161: RuntimeWarning: invalid value encountered in double_scalars
>   ret = ret.dtype.type(ret / rcount)
> Traceback (most recent call last):
>   File "eval_ap.py", line 175, in <module>
>     num_true_examples = y_true_sorted_cumsum[-1]
> IndexError: index -1 is out of bounds for axis 0 with size 0

I guess the problem comes from the pre-trained models that you provided. I don't understand why there is a 'scenc.pth' instead of 'abc.pth' in the Zip archive "abc.pth".

Thanks in advance and looking forwards to your respond.

Best and have a nice day.

Hello all,

Does anybony managed to install it on Windows ? It fails at the python setup.py bdist_wheel inside /src/lib/spconv.

I saw that there is a version of spconv in a different repo that can be installed on Windows but I'm not sure how I can deal with that change. https://github.com/traveller59/spconv/

Any help is welcome, if I go further in my troubleshooting I'll post here.

Thank you CM

when running compile i got ERROR: spconv-1.0-cp37-cp37m-linux_x86_64.whl is not a supported wheel on this platform. my platform is python 3.6 CUDA 10.2 pytorch 1.10.1 and i want to know the version of yours

Hello,

Thanks for providing the source code.

I tried to use your code to segment a point cloud. I noticed that your code directly read the edge information from the '.npz' files. In your paper, you said that 'Otherwise we generate k=16 nearest neighbors from each point to form E'. So I think your code has the ability to segment a point cloud without providing 'F' in the input file, right? Can you explain how to do that?

Thanks in advance. Best. Mulin

Hi, thanks for your work.

Could you update the download link for the data and pre-trained model? This original link is broken: https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/3d/PrimitiveNet

Thanks for sharing the great work. I try to reproduce the algorithm but the wrong edge link make the results bad. I want to know what is the accuracy of positive and negative samples in edge prediction and whether wrong connections will affect the final result？

Hello, thank you for your open source code. I am using sh scripts/test_ sence. sh encountered the following problem when executing the command, which was caused by mismatched parameters. Please tell me your sense.pthfile How did you get it? Can you share it? Error(s) in loading state_dict for SemanticPrediction: size mismatch for input_conv.0.weight: copying a param with shape torch.Size([3, 3, 3, 16, 16]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3, 16]). size mismatch for unet.blocks.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 16, 16]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3, 16]). size mismatch for unet.blocks.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 16, 16]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3, 16]). size mismatch for unet.blocks.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 16, 16]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3, 16]). size mismatch for unet.blocks.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 16, 16]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3, 16]). size mismatch for unet.conv.2.weight: copying a param with shape torch.Size([2, 2, 2, 16, 32]) from checkpoint, the shape in current model is torch.Size([32, 2, 2, 2, 16]). size mismatch for unet.u.blocks.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 32, 32]) from checkpoint, the shape in current model is torch.Size([32, 3, 3, 3, 32]). size mismatch for unet.u.blocks.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 32, 32]) from checkpoint, the shape in current model is torch.Size([32, 3, 3, 3, 32]). size mismatch for unet.u.blocks.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 32, 32]) from checkpoint, the shape in current model is torch.Size([32, 3, 3, 3, 32]). size mismatch for unet.u.blocks.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 32, 32]) from checkpoint, the shape in current model is torch.Size([32, 3, 3, 3, 32]). size mismatch for unet.u.conv.2.weight: copying a param with shape torch.Size([2, 2, 2, 32, 48]) from checkpoint, the shape in current model is torch.Size([48, 2, 2, 2, 32]). size mismatch for unet.u.u.blocks.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 48, 48]) from checkpoint, the shape in current model is torch.Size([48, 3, 3, 3, 48]). size mismatch for unet.u.u.blocks.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 48, 48]) from checkpoint, the shape in current model is torch.Size([48, 3, 3, 3, 48]). size mismatch for unet.u.u.blocks.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 48, 48]) from checkpoint, the shape in current model is torch.Size([48, 3, 3, 3, 48]). size mismatch for unet.u.u.blocks.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 48, 48]) from checkpoint, the shape in current model is torch.Size([48, 3, 3, 3, 48]). size mismatch for unet.u.u.conv.2.weight: copying a param with shape torch.Size([2, 2, 2, 48, 64]) from checkpoint, the shape in current model is torch.Size([64, 2, 2, 2, 48]). size mismatch for unet.u.u.u.blocks.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 64, 64]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3, 64]). size mismatch for unet.u.u.u.blocks.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 64, 64]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3, 64]). size mismatch for unet.u.u.u.blocks.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 64, 64]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3, 64]). size mismatch for unet.u.u.u.blocks.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 64, 64]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3, 64]). size mismatch for unet.u.u.u.conv.2.weight: copying a param with shape torch.Size([2, 2, 2, 64, 80]) from checkpoint, the shape in current model is torch.Size([80, 2, 2, 2, 64]). size mismatch for unet.u.u.u.u.blocks.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 80, 80]) from checkpoint, the shape in current model is torch.Size([80, 3, 3, 3, 80]). size mismatch for unet.u.u.u.u.blocks.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 80, 80]) from checkpoint, the shape in current model is torch.Size([80, 3, 3, 3, 80]). size mismatch for unet.u.u.u.u.blocks.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 80, 80]) from checkpoint, the shape in current model is torch.Size([80, 3, 3, 3, 80]). size mismatch for unet.u.u.u.u.blocks.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 80, 80]) from checkpoint, the shape in current model is torch.Size([80, 3, 3, 3, 80]). size mismatch for unet.u.u.u.u.conv.2.weight: copying a param with shape torch.Size([2, 2, 2, 80, 96]) from checkpoint, the shape in current model is torch.Size([96, 2, 2, 2, 80]). size mismatch for unet.u.u.u.u.u.blocks.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 96, 96]) from checkpoint, the shape in current model is torch.Size([96, 3, 3, 3, 96]). size mismatch for unet.u.u.u.u.u.blocks.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 96, 96]) from checkpoint, the shape in current model is torch.Size([96, 3, 3, 3, 96]). size mismatch for unet.u.u.u.u.u.blocks.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 96, 96]) from checkpoint, the shape in current model is torch.Size([96, 3, 3, 3, 96]). size mismatch for unet.u.u.u.u.u.blocks.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 96, 96]) from checkpoint, the shape in current model is torch.Size([96, 3, 3, 3, 96]). size mismatch for unet.u.u.u.u.u.conv.2.weight: copying a param with shape torch.Size([2, 2, 2, 96, 112]) from checkpoint, the shape in current model is torch.Size([112, 2, 2, 2, 96]). size mismatch for unet.u.u.u.u.u.u.blocks.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 112, 112]) from checkpoint, the shape in current model is torch.Size([112, 3, 3, 3, 112]). size mismatch for unet.u.u.u.u.u.u.blocks.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 112, 112]) from checkpoint, the shape in current model is torch.Size([112, 3, 3, 3, 112]). size mismatch for unet.u.u.u.u.u.u.blocks.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 112, 112]) from checkpoint, the shape in current model is torch.Size([112, 3, 3, 3, 112]). size mismatch for unet.u.u.u.u.u.u.blocks.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 112, 112]) from checkpoint, the shape in current model is torch.Size([112, 3, 3, 3, 112]). size mismatch for unet.u.u.u.u.u.deconv.2.weight: copying a param with shape torch.Size([2, 2, 2, 112, 96]) from checkpoint, the shape in current model is torch.Size([96, 2, 2, 2, 112]). size mismatch for unet.u.u.u.u.u.blocks_tail.block0.i_branch.0.weight: copying a param with shape torch.Size([1, 1, 1, 192, 96]) from checkpoint, the shape in current model is torch.Size([96, 1, 1, 1, 192]). size mismatch for unet.u.u.u.u.u.blocks_tail.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 192, 96]) from checkpoint, the shape in current model is torch.Size([96, 3, 3, 3, 192]). size mismatch for unet.u.u.u.u.u.blocks_tail.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 96, 96]) from checkpoint, the shape in current model is torch.Size([96, 3, 3, 3, 96]). size mismatch for unet.u.u.u.u.u.blocks_tail.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 96, 96]) from checkpoint, the shape in current model is torch.Size([96, 3, 3, 3, 96]). size mismatch for unet.u.u.u.u.u.blocks_tail.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 96, 96]) from checkpoint, the shape in current model is torch.Size([96, 3, 3, 3, 96]). size mismatch for unet.u.u.u.u.deconv.2.weight: copying a param with shape torch.Size([2, 2, 2, 96, 80]) from checkpoint, the shape in current model is torch.Size([80, 2, 2, 2, 96]). size mismatch for unet.u.u.u.u.blocks_tail.block0.i_branch.0.weight: copying a param with shape torch.Size([1, 1, 1, 160, 80]) from checkpoint, the shape in current model is torch.Size([80, 1, 1, 1, 160]). size mismatch for unet.u.u.u.u.blocks_tail.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 160, 80]) from checkpoint, the shape in current model is torch.Size([80, 3, 3, 3, 160]). size mismatch for unet.u.u.u.u.blocks_tail.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 80, 80]) from checkpoint, the shape in current model is torch.Size([80, 3, 3, 3, 80]). size mismatch for unet.u.u.u.u.blocks_tail.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 80, 80]) from checkpoint, the shape in current model is torch.Size([80, 3, 3, 3, 80]). size mismatch for unet.u.u.u.u.blocks_tail.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 80, 80]) from checkpoint, the shape in current model is torch.Size([80, 3, 3, 3, 80]). size mismatch for unet.u.u.u.deconv.2.weight: copying a param with shape torch.Size([2, 2, 2, 80, 64]) from checkpoint, the shape in current model is torch.Size([64, 2, 2, 2, 80]). size mismatch for unet.u.u.u.blocks_tail.block0.i_branch.0.weight: copying a param with shape torch.Size([1, 1, 1, 128, 64]) from checkpoint, the shape in current model is torch.Size([64, 1, 1, 1, 128]). size mismatch for unet.u.u.u.blocks_tail.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 128, 64]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3, 128]). size mismatch for unet.u.u.u.blocks_tail.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 64, 64]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3, 64]). size mismatch for unet.u.u.u.blocks_tail.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 64, 64]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3, 64]). size mismatch for unet.u.u.u.blocks_tail.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 64, 64]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3, 64]). size mismatch for unet.u.u.deconv.2.weight: copying a param with shape torch.Size([2, 2, 2, 64, 48]) from checkpoint, the shape in current model is torch.Size([48, 2, 2, 2, 64]). size mismatch for unet.u.u.blocks_tail.block0.i_branch.0.weight: copying a param with shape torch.Size([1, 1, 1, 96, 48]) from checkpoint, the shape in current model is torch.Size([48, 1, 1, 1, 96]). size mismatch for unet.u.u.blocks_tail.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 96, 48]) from checkpoint, the shape in current model is torch.Size([48, 3, 3, 3, 96]). size mismatch for unet.u.u.blocks_tail.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 48, 48]) from checkpoint, the shape in current model is torch.Size([48, 3, 3, 3, 48]). size mismatch for unet.u.u.blocks_tail.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 48, 48]) from checkpoint, the shape in current model is torch.Size([48, 3, 3, 3, 48]). size mismatch for unet.u.u.blocks_tail.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 48, 48]) from checkpoint, the shape in current model is torch.Size([48, 3, 3, 3, 48]). size mismatch for unet.u.deconv.2.weight: copying a param with shape torch.Size([2, 2, 2, 48, 32]) from checkpoint, the shape in current model is torch.Size([32, 2, 2, 2, 48]). size mismatch for unet.u.blocks_tail.block0.i_branch.0.weight: copying a param with shape torch.Size([1, 1, 1, 64, 32]) from checkpoint, the shape in current model is torch.Size([32, 1, 1, 1, 64]). size mismatch for unet.u.blocks_tail.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 64, 32]) from checkpoint, the shape in current model is torch.Size([32, 3, 3, 3, 64]). size mismatch for unet.u.blocks_tail.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 32, 32]) from checkpoint, the shape in current model is torch.Size([32, 3, 3, 3, 32]). size mismatch for unet.u.blocks_tail.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 32, 32]) from checkpoint, the shape in current model is torch.Size([32, 3, 3, 3, 32]). size mismatch for unet.u.blocks_tail.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 32, 32]) from checkpoint, the shape in current model is torch.Size([32, 3, 3, 3, 32]). size mismatch for unet.deconv.2.weight: copying a param with shape torch.Size([2, 2, 2, 32, 16]) from checkpoint, the shape in current model is torch.Size([16, 2, 2, 2, 32]). size mismatch for unet.blocks_tail.block0.i_branch.0.weight: copying a param with shape torch.Size([1, 1, 1, 32, 16]) from checkpoint, the shape in current model is torch.Size([16, 1, 1, 1, 32]). size mismatch for unet.blocks_tail.block0.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 32, 16]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3, 32]). size mismatch for unet.blocks_tail.block0.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 16, 16]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3, 16]). size mismatch for unet.blocks_tail.block1.conv_branch.2.weight: copying a param with shape torch.Size([3, 3, 3, 16, 16]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3, 16]). size mismatch for unet.blocks_tail.block1.conv_branch.5.weight: copying a param with shape torch.Size([3, 3, 3, 16, 16]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3, 16]). size mismatch for linear_semantics.weight: copying a param with shape torch.Size([2, 32]) from checkpoint, the shape in current model is torch.Size([10, 32]). size mismatch for linear_semantics.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([10]).

Hello! Great work! I have a little trouble to downloading files from download.sh. If I'm not wrong, pan.baidu is not working or working slow for a lot of people. Can you please upload to other storage cloud service(for example google drive), as an alternative to pan.baidu, if it is not too hard.

Hi jingwei, I am currently following your wonderful work. After running your code, I have some questions about the dataset.

First, in dataset.py, I consider F and SF as faces and the primitive type of faces. But the numbers of F is much more than xyz_origin which is strange. So, what's the meaning of F and SF and why don't just use primitive type and primitive idx of each point, just like ParseNet and others? xyz_origin, normal, boundary, F, SF = data['V'], data['N'], data['B'], data['F'], data['S']

Second, also in dataset.py, I consider the variable 'semantic' as the primitive type of each point. And this variable also be packed into batch['semantic_gt'] as ground truth. semantics = np.zeros((xyz_origin.shape[0]), dtype='int32') semantics[F[:, 0]] = SF; semantics[F[:, 1]] = SF; semantics[F[:, 2]] = SF But when I visualize one point cloud and add colors to each point according to 'semantics', the visualization results and color_map are blow: The orange part seems incorrect which a spline is labeled as a plane. And the cyclinder in purple also is labeled as cone.

color_map={

    # (key:value  represents  primitiveType: rgb)
    1: [255, 127, 14],  # plane         orange
    3: [148, 103, 189],  # cone        purple
    4: [31, 119, 180],  # cyclinder   blue
    5: [44, 160, 44],  # sphere         green

    2: [220,220,220],  # open b-spline  gray
    8: [220,220,220],  # open b-spline  gray
    0: [220,220,220],  # closed b-spline  gray
    6: [220,220,220],  # closed b-spline  gray
    7: [220,220,220],  # closed b-spline  gray
    9: [220,220,220],  # closed b-spline  gray
}

So, my question is, did the [1,3,4,5] represents to [plane, cone, cyclinder, sphere] separately just like ParseNet? Or you may use other representation?

Thanks in advance for your reply and code!