r"""Check gradients computed via small finite differences against analytical gradients w.r.t. tensors in :attr:`inputs` that are of floating point

r"""Create a `ME.SparseTensor` coordinates from a sequence of coordinates Given a list of either numpy or pytorch tensor coordinates, return the

Adds a value to the back.

* Kernel map ****************************************************************************/

coordinate_size functions

r"""create a new coordinate map and returns (key, (map, inverse_map)). :attr:`coordinates`: `torch.Tensor` (Int tensor. `CUDA` if coo

allocator backend will be ignored when coordinate map backend is CPU

\brief Resizes the array, making it either larger or smaller. Initializes new elements with `newval`.

key functions

r"""Converts the current sparse tensor field to a sparse tensor.

r"""Given coordinates, and features (optionally labels), the function generates quantized (voxelized) coordinates. Args: :attr:`coord

r"""a high-dimensional sparse average pooling layer. Args: :attr:`kernel_size` (int, optional): the size of the kernel in the

* @brief given a key iterator begin-end pair and a value iterator begin-end * pair, insert all elements. * * @return none */

r"""Generate a new coordinate map and returns the key. :attr:`coordinate_map_key` (:attr:`MinkowskiEngine.CoordinateMapKey`): input m

Calculate cross entropy loss, apply label smoothing if needed.

Return quaternion from rotation matrix. If isprecise is True, the input matrix is assumed to be a precise rotation matrix and a faster algori

helper functions

* @brief Get raw pointer to underlying NVTX attributes object. * */

r"""Get kernel in-out maps for the specified coords keys or tensor strides. returns dict{kernel_index: in_out_tensor} where in_out_tensor[0]

forwards the index by one, wrapping around at the end