goodok/fastai_sparse
3D augmentation and transforms of 2D/3D sparse data, such as 3D triangle meshes or point clouds in Euclidean space. Extension of the Fast.ai library to train Sub-manifold Sparse Convolution Networks
Jupyter NotebookMIT
Issues
- 0
mesh flipX: During the flipX transformation of the meshes the normals (wich are re-calculated later) are inverted.
#14 opened by goodok - 1
- 0
color noise it not color noise
#11 opened by roma-goodok - 1
random sampling points from points cloud by _sample_point transform returns doubled points
#8 opened by roma-goodok - 1
watermark - virtualenv returns None
#5 opened by roma-goodok