robotgradient / grasp_diffusion

Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home
MIT License
234 stars 24 forks source link

Error following steps for dataset generation step 1 #13

Open ignpaub opened 4 months ago

ignpaub commented 4 months ago

Good morning:

I'm folllowing proposed steps to generate the dataset starting from ShapeNetSem. When running grasp_difussion/scripts/create_data/simplify.sh changing the paths, an error arose:

100f39dce7690f59efb94709f30ce0d2.obj
manifold 100f39dce7690f59efb94709f30ce0d2.obj temp.watertight.obj 20000
simplify: /Manifold/3rd/igl/per_vertex_point_to_plane_quadrics.cpp:83: igl::per_vertex_point_to_plane_quadrics(const MatrixXd&, const MatrixXi&, const MatrixXi&, const MatrixXi&, const MatrixXi&, std::vector<std::tuple<Eigen::Matrix<double, -1, -1, 0, -1, -1>, Eigen::Matrix<double, 1, -1, 1, 1, -1>, double> >&)::<lambda(const RowVectorXd&, const MatrixXd&, double)>: Assertion `std::abs(S.row(j).dot(ei)) < 1e-10' failed.
simplify.sh: line 9: 72944 Aborted                 (core dumped) $path_manifold/simplify -i temp.watertight.obj -o $filename -m -r 0.02

Files are available here: https://drive.google.com/drive/folders/1XpUyj65nVRU9RZ6qfWiySH7GHOnyv3Ae?usp=sharing

Some solutions have been provided on the internet, such as https://github.com/NVlabs/acronym/issues/3 or https://github.com/hjwdzh/Manifold/issues/5.

However, how did you address this issue?

Thanks a lot.

Ignacio.