train on a custom dataset

[LeroyChou]

I'm trying to train surfemb on a custom dataset. But when I do inference, I find some files/dirs are musts(they're detection_results, surface_samples, surface_samples_normals). For dectection_results, I've already known it's from CosyPose, but I don't know how to generate it in detail. For surface_samples, I followed your guidance that run command $ python -m surfemb.scripts.misc.surface_samples_remesh_visible clip first. But I encountered this error:

Traceback (most recent call last):
  File "/root/miniconda3/envs/surfemb/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/root/miniconda3/envs/surfemb/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/root/surfemb/surfemb/scripts/misc/surface_samples_remesh_visible.py", line 32, in <module>
    ms.compute_scalar_ambient_occlusion(occmode='per-Face (deprecated)', reqviews=256)
AttributeError: 'pymeshlab.pmeshlab.MeshSet' object has no attribute 'compute_scalar_ambient_occlusion'

Could you please give me any suggestions on these two problems?

[LeroyChou]

The second problem has been addressed. coverting pymeshlab to version 0.2 works.

[rasmushaugaard]

Hi

Perhaps you can get some inspiration from the script that loads the cosypose detections and saves them, here.

BR Rasmus

[LeroyChou]

Thank you. I've been studying cosypose's codes these day, and your suggestions help me a lot.

[smoothumut]

The second problem has been addressed. coverting pymeshlab to version 0.2 works.

Hi LeroyChou, I am having problem with

ms.ambient_occlusion(occmode='per-Face (deprecated)', reqview=256)

this line stops the code without giving any error. Did you have the same problem? if so, how did you solve it? thanks in advance

[LeroyChou]

The second problem has been addressed. coverting pymeshlab to version 0.2 works.

Hi LeroyChou, I am having problem with

ms.ambient_occlusion(occmode='per-Face (deprecated)', reqview=256)

this line stops the code without giving any error. Did you have the same problem? if so, how did you solve it? thanks in advance

hello. yes I was troubled by the same problem. My solution is converting the pymeshlab's version to 0.2 and it works in my case.