Install ERROR: Command errored out with exit status 1 about lightconvpoint HOT 9 OPEN

have you solved it？

from lightconvpoint.

have you solved it？

Not yet.
The same thing happens to you?
Any idea?

from lightconvpoint.

have you solved it？

Not yet. The same thing happens to you? Any idea?

The same thing happens to me...
By the way ,Do you have any recommended repositories for point cloud semantic segmentation? (better if it can be trained fast and has higher mIOU)

from lightconvpoint.

Hello,
Thanks for the issue.
I am planning to release a version without C++ module compilation by the end of the month (March).
Like that, it should rely only on PyTorch and maybe on TorchGeometric.
The code is almost ready, I have to make sure it is still compatible with the pre-trained networks I provided.
Best,

from lightconvpoint.

Hello, Thanks for the issue. I am planning to release a version without C++ module compilation by the end of the month (March). Like that, it should rely only on PyTorch and maybe on TorchGeometric. The code is almost ready, I have to make sure it is still compatible with the pre-trained networks I provided. Best,

Great.
Thanks for all your work. I will expect the update.

from lightconvpoint.

have you solved it？

Not yet. The same thing happens to you? Any idea?

The same thing happens to me... By the way ,Do you have any recommended repositories for point cloud semantic segmentation? (better if it can be trained fast and has higher mIOU)

I've been using the Open3D ML module (https://github.com/isl-org/Open3D-ML). They have different state-of-the-art architectures implemented and pretrained. It supposed to be easier to use than the original implementations.

from lightconvpoint.

have you solved it？

Not yet. The same thing happens to you? Any idea?

The same thing happens to me... By the way ,Do you have any recommended repositories for point cloud semantic segmentation? (better if it can be trained fast and has higher mIOU)

I've been using the Open3D ML module (https://github.com/isl-org/Open3D-ML). They have different state-of-the-art architectures implemented and pretrained. It supposed to be easier to use than the original implementations.

Nice, thank a lot!
Best wishes!

from lightconvpoint.

Hello, can you tell me what the meaning of 2500000 in prepare_data.py is? thanks.

from lightconvpoint.

I want use the code to run own datasets!

from lightconvpoint.