sparse_rpn about second.pytorch

[traveller59]

I have implemented the sparse rpn but the running speed is greatly decreased. for 2D RPN you can try SBNet, the SparseConvNet is slow when the sparsity grows ( the normal sparse conv increase sparsity rapidly).

[roma-goodok]

SparseConvNet is slow when the sparsity grows ( the normal sparse conv increase sparsity rapidly).

Just to be sure, sparsity (share of empty voxels) or density (share of non empty voxels) ? May be I am wrong, but my undesrtanding that SparseConvNet is slow when sparsity becomes low (as it mentioned in the SBNet papers) and normal sparse conv without submanifold/blocks decrease sparsity rapidly.

[traveller59]

@roma-goodok you are right, that's my mistake...
One of the major reason why SparseConvNet conv performance is rule generation (used for gather-gemm-scatter algorithm of sparse conv) is very slow (run on CPU). less sparsity of data, more rule generation time.