* \brief Checks if the this matrix has exclusive use to the underlying data, i.e. no other matrix expression shares the data. * This allows to ch

Dampen the learning rates. Arguments: step (int): The index of current step. (Default: None)

* \brief Computes the determinant of this matrix * \return The determinant */

* \brief Frees memory previously allocated with allocateDevice(size_t). * Passing a NULL-pointer should be a no-op. * \param memory the memory to be

Return a window function. Args: win_type (str): Window type. Can either be one of the window function provided in PyTorch ['h

* \brief Checks if the this matrix has exclusive use to the underlying data, i.e. no other matrix expression shares the data. * \b Note: The data

Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as ten

Generate random quaternions representing rotations, i.e. versors with nonnegative real part. Args: n: Number of quaternions in a

* Records an event into this instance after all preceding operations in <code>stream</code> have been completed. */

* Synchronizes the given stream with this event. * The given stream will wait until the event recorded with \ref record(cudaStream_t) has completed.

Converts CamelCase string into snake_case.

* \brief Initializes the Conjugate Gradient with the specified matrix. * The preconditioner is created with \code Preconditioner(matrix) \endcode

* \brief Initializes this SparseMatrix with the given sparsity pattern and (if not fixed by the template argument) * with the given number of bat

Return a tensor where each element has the absolute value taken from the, corresponding element of a, with sign taken from the corresponding

* \brief Checks with assertions that this SparsityPattern is valid. */

* \brief Returns the number of batches of this matrix. * \returns the number of batches. */