Alexandre Boulch
Alexandre Boulch
Radius CPU computation with KDTree.query() when number of neighbors is higher than max_num_neighbors
The GPU version does as expected.
Radius CPU computation with KDTree.query() when number of neighbors is higher than max_num_neighbors
Thanks for qucik response. I was not on the right version of the code documentation. I use the 1.5.9 version of the code see bellow In an IPython session: ```python...
Radius CPU computation with KDTree.query() when number of neighbors is higher than max_num_neighbors
Hello, Problem could be that nanoflann does not produce results in a random order when lookning for the neighbors in a given radius. This is due the tree traversal process....
I fixed compilation problems. Updated Eigen and Nanoflann. Seems to work fine on fresh ubuntu 18.04 install + Anaconda
Hello, At training, the `iter` parameter is acually the number of batch in one epoch. It is true that is has a great impact: the number of training step on...
Hello, At training blocks are not predefined but randomly sampled.
Hello, I am sorry for the late response. I cannot test on Windows.
Hello, I updated the repository to make it possible to install with pip. Should be better, tell me if something is wrong.
Hello, I fixed compilation for Ubuntu 18.04 and Anaconda. Tell me if it works for you. Best, Alexandre
Hello, I have added pre-trained models on NPM3D and released the fusion code. The pre-trained models come with no guarantee as I changed affiliation and could not retreive all data...