Migration Guide from v0.4.x to 0.5.x

Sparse Tensor

Input Keywords

Abbreviated keywords to complete keywords.

import MinkowskiEngine as ME

...

# v0.4.x
sinput = ME.SparseTensor(feats, coords=coords)
manager = sinput.coords_man
key = sinput.coords_key
# v0.5.x
sinput = ME.SparseTensor(feats, coordinates=coords)
manager = sinput.coordinate_manager
key = sinput.coordinate_map_key

CUDA acceleration

In v0.4, the CUDA acceleration was supported for matrix multiplication (convolution), but from v0.5.0a, we provide CUDA backends for kernel map generation. However, to use the CUDA acceleration, you must provide coordinates as a CUDA tensor.

# v0.4.x
sinput = ME.SparseTensor(feats, coords=coords).to(0)
# v0.5.x
# The following line throws an error
# sinput = ME.SparseTensor(feats, coordinates=coords).to(0)
sinput = ME.SparseTensor(feats.to(0), coordinates=coords.to(0))

Convolution / ConvolutionTranspose

Use the standard pytorch keywords.

# v0.4.x
conv = ME.MinkowskiConvolution(,... has_bias=False)
# v0.5.x
conv = ME.MinkowskiConvolution(,... bias=False)