uncbiag/shapmagn

shape registration

shapmagn's Issues

is this run in linux or windows

is this run in linux or windows

Cannot reproduce Robust Optimal Transport

Hi, thanks for your work!

I just had a try of the Robust Optimal Transport.
But the results are different from the provided GIF.
Some keyframes are as below:

Problem install setup.py

When I execute
python setup.py install

I get the error
error: command 'gcc' failed with exit status 1

ERROR:root:bad X server connection. DISPLAY=

[KeOps] Warning : cuda was detected, but driver API could not be initialized. Switching to cpu only.
open3d is not detected, related functions are disabled
Teaser is not detected, related functions are disabled
torch scatter is not detected, voxel grid sampling is disabled
the source and the target min interval is 0.0006067752838134766,0.0006067752838134766
Creating key = record_path; category = root; value = ./output/toy_demo/gradient_flow
Creating key = interpolator_obj; category = root; value = point_interpolator.nadwat_kernel_interpolator(scale=0.1, exp_order=2)
Creating new category: root.sim_loss
Creating key = loss_list; category = root.sim_loss; value = ['geomloss']
Creating new category: root.sim_loss.geomloss
Creating key = attr; category = root.sim_loss.geomloss; value = points
Creating key = geom_obj; category = root.sim_loss.geomloss; value = geomloss.SamplesLoss(loss='sinkhorn',blur=0.0003033876419067383, scaling=0.8,debias=False)
Creating new category: root.geom_loss_opt_for_eval
Using default value = for key = external_evaluate_metric_obj of category = root
Using default value = 1 for key = print_step of category = root
Using default value = True for key = save_res of category = root
Using default value = 1 for key = save_3d_shape_every_n_iter of category = root
Using default value = 1 for key = save_2d_capture_every_n_iter of category = root
Using default value = visualizer.capture_plotter() for key = capture_plot_obj of category = root
0.0 th step, sim_loss is 77.8389892578125
/usr/local/lib/python3.10/dist-packages/pyvista/plotting/plotting.py:148: UserWarning:
This system does not appear to be running an xserver.
PyVista will likely segfault when rendering.

Try starting a virtual frame buffer with xvfb, or using
pyvista.start_xvfb()

warnings.warn(
2023-06-16 10:15:43.575 ( 6.656s) [ 8A4FA740