pranavkdm / r-pointhop Goto Github PK
View Code? Open in Web Editor NEWR-PointHop: A Green, Accurate and Unsupervised Point Cloud Registration Method
R-PointHop: A Green, Accurate and Unsupervised Point Cloud Registration Method
Could you tell me how to train the network using my own data ?
Just change the train_data in the train.py ?
my pc with 16GB RAM can not run the train. It can not return from 'knn' function in point_utils.py
I have changed it into not using threading and changed the batch_size to smaller. It still not works.
Hi,
Thank you for releasing your codes, and it is a really excellent job! I wonder to reproduce the results on the partial-to-partial registration data, but I fail to find the settings of this experiment, such as the numbers of sample points and the numbers of the neighbors. Besides, I have no idea about that if the model needs to be re-trained on the partial data, or the released model can be used to register the partial inputs directly. Hope you can answer my doubts.
python train.py --first_20 False
Traceback (most recent call last):
File "train.py", line 51, in
main()
File "train.py", line 42, in main
train_data = train_data[train_label<20]
IndexError: boolean index did not match indexed array along dimension 1; dimension is 1024 but corresponding boolean dimension is 1
python test.py --source ./data/source_0.ply --target ./data/target_0.ply
munmap_chunk(): invalid pointer
(core dumped)
Is it because of the version of the installation library?
Could you tell me about your library version?
I trained the network following the README Training part.
I am wondering how to reproduce the test results in the paper.
Hi,
Thank you for releasing your codes, and it is a really excellent job!I noticed that you and your partner published an updated version of this paper in March 2022, which contains 3dmach dataset, but the code of the paper has not been updated. Can you publish the new code?Thank you again.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.