get_mask_2d_greedy¶

paddle.fluid.contrib.sparsity.utils. get_mask_2d_greedy ( mat, n, m ) [source]

Greedily generate 2D n:m sparse pattern mask of the input matrix mat. This function would pad each dimension of mat by zero to be a multiples of m before mask generation.

2D n:m sparse pattern: At least \(n \times n\) zeros in every \(m \times m\) block under the constraint of at least n zeros for each row and column. Greedily generating: For each \(m \times m\) block, selecting values to keep in descent order.

Parameters

• mat (nparray) – The input matrix.

• n (int) – n of n:m sparse pattern.

• m (int) – m of n:m sparse pattern.

Returns

The 2D n:m sparse mask of mat.

Return type

nparray

Examples

import numpy as np
import paddle.fluid.contrib.sparsity as sparsity

mat = np.array([[9, 8, 3, 7],
                [9, 2, 1, 10],
                [5, 1, 3, 6],
                [2, 4, 6, 1]])
mask = sparsity.get_mask_2d_greedy(mat, 2, 4)
# nparray([[1. 1. 0. 0.]
#          [1. 0. 0. 1.]
#          [0. 0. 1. 1.]
#          [0. 1. 1. 0.]])
sparsity.check_mask_2d(mask, 2, 4) # True