Closed eyildiz-ugoe closed 5 years ago
your model is in meters, did you change the vertex_scale parameter to 1000? (it's required in mm) Please do that and set the model parameter to cad again
@MartinSmeyer Hi, for some reason I cannot see the reply in any of the issues but I have it in my e-mail, hence I am replying here.
Thank you for your rapid response. I have acquired the models from another source, and yes I have confirmed that they are scaled. However, I don't know how to change this parameter. Is it on Blender? If so, could you tell me how you did it? I know it's not related to this repository but I really would like to try the Encoder, therefore I would appreciate if you could tell me how to set it back.
Your segmentation fault is not related to
"ValueError: need more than 3 values to unpack"
which only happens if no vertex color is found in the 3d model while the MODEL parameter is set to "reconst".
I just meant the vertex_scale parameter in the training config.
Closing this issue because of the duplicate.
see [#10]
Hey, were you able to solve this problem? I'm facing the exact same issue.
Update : It works fine on using the models_reconst from the t-less_v2 dataset. Cannot figure out with the models_cad
I'm trying to run
ae_train exp_group/my_autoencoder -d
with a .ply model of mine (which is not a CAD model) and I receive the following error:Note that the suggestion reported in https://github.com/DLR-RM/AugmentedAutoencoder/issues/7, did not solve my problem. And if I change it to cad in the config file, I get a
Segmentation Fault
.In order to help debugging, I am also sharing my .ply model with you: bay.ply My Blender can visualize this .ply, so I don't think the problem lies within there.