jax.experimental.sparse.csr_matmat# jax.experimental.sparse.csr_matmat(mat, B, *, transpose=False)[source]# Product of CSR sparse matrix and a dense matrix. Parameters: mat (CSR) – CSR matrix B (Array) – array of shape (mat.shape[0] if transpose else mat.shape[1], cols) and dtype mat.dtype transpose (bool) – boolean specifying whether to transpose the sparse matrix before computing. Returns: array of shape (mat.shape[1] if transpose else mat.shape[0], cols)representing the matrix vector product. Return type: C