r"""Returns the coordinates map key.

r"""Helper function that retrieves the first coordinate map key for the given tensor stride.

Returns 1 if key is found, 0 otherwise.

r"""Convert the :attr:`MinkowskiEngine.SparseTensor` to a torch dense tensor. Args: :attr:`shape` (torch.Size, optional):

* @brief strided coordinate map for region. */

r"""convolution on a sparse tensor Args: :attr:`in_channels` (int): the number of input channels in the input tensor.

r"""Helper function to convert :attr:`MinkowskiEngine.MinkowskiBatchNorm` layer in the model to :attr:`MinkowskiEngine.MinkowskiSyncBa

r"""Return coordinates at the specified batch index. Returns a torch.IntTensor :math:`C \in \mathcal{R}^{N_i \times D}` coordinates a

Returns a pointer to the underlying data

Returns an iterator to the end

* @brief Return the NVTX color type of the color. * */

* @brief Returns the `color`s argb hex code * */

Hash an arbitrary amount of bytes. This is basically Murmur2 hash without caring about big endianness. TODO(martinus) add a fallback for very large st

r"""Convert a batched tensor (dimension 0 is the batch dimension) to a SparseTensor :attr:`x` (:attr:`torch.Tensor`): a batched tensor. The first

Returns an iterator to the beginning

r""" Args: :attr:`X` (:attr:`MinkowskiEngine.SparseTensor`): a sparse tensor that discretized the original input.

Computer the transformation error as an approximation of the RMSE of corresponding points. More informaiton at http://redwood-data.org/indoor

does not actually deallocate but puts it in store. make sure you have already called the destructor! e.g. with obj->~T(); pool.deallocate(obj);

coordinates = dense_coordinates(tensor.shape)

r"""Returns a feature matrix at the specified batch index. Returns a torch.Tensor :math:`C \in \mathcal{R}^{N \times N_F}` feature ma

r"""Return the current global coordinate manager

* @brief Returns the type identifier **/

* Given a continuous tensor field, return the weights and associated kernel * map */