OverlapPredator

OverlapPredator copied to clipboard

@ShengyuH Could you please let me know how you preprocessed the 3DMatch dataset to get the rotation and translation matrix for the pair of point clouds, that we use to...

pomo1144

Huaixv17

First, thank you for this solid work! As we want to further explore this work, I wonder if you would like to share the preprocess script on 3DMatch dataset for...

xl-huo

Inference does not get applied

8

Hello everyone, thank you very much for your work! After setting up your project on a Win10 machine with a dedicated conda environment I got following result:  Everything seems...

Birkenpapier

I want to know where to download 3dmatch dataset in .pth format?

33

The 3dmatch dataset download link for this repository give us the dataset in .ply format, and the folder branch doesn't match the path in .pkl file. Where should I download...

superYuezhang

Requirements not match

4

why does running pip install requirements.txt saying that some packages listed in the requirements requires at least python 3.9 and why does torch-1.7.1-cp38-cp38-win_amd64.whl is not at all compatiable with torchvision==0.8.2?...

lucienchia

Training is done with a warning message from the Scikit-Learn library

5

/home/ssf/.conda/envs/geotransformer/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1245: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result)) Will this...

LittleFay2

Updated to work with Python 3.10, Pytorch 2.0.1 and Cuda 11.7

1

marcofariasmx

export the model to torchscript?

4

Could we export such model to torchscript? I found that it has error due to calling c++ function grid_subsampling and cpp_neighbors

keepgoing2996

Questions about producing the newest results with the newest codes

4

Hi! Thank you so much for this amazing work! I'm trying to produce the results with your newest codes. I followed the guidance in README and got beautiful results as...

HowLeeHi