方法1：

label = label.T[::-1].transpose()

方法2：

label = label[:,::-1]

方法3：

使用 numpy.fliplr

https://docs.scipy.org/doc/numpy/reference/generated/numpy.fliplr.html

numpy.fliplr

numpy.fliplr(m)[source]

Flip array in the left/right direction.

Flip the entries in each row in the left/right direction. Columns are preserved, but appear in a different order than before.

Parameters:	m : array_like Input array, must be at least 2-D.
Returns:	f : ndarray A view of m with the columns reversed. Since a view is returned, this operation is .

See also

flipud

Flip array in the up/down direction.

rot90

Rotate array counterclockwise.

Notes

Equivalent to m[:,::-1]. Requires the array to be at least 2-D.

Examples

>>> A = np.diag([1.,2.,3.])
>>> A
array([[ 1.,  0.,  0.],
       [ 0.,  2.,  0.],
       [ 0.,  0.,  3.]])
>>> np.fliplr(A)
array([[ 0.,  0.,  1.],
       [ 0.,  2.,  0.],
       [ 3.,  0.,  0.]])
>>> A = np.random.randn(2,3,5)
>>> np.all(np.fliplr(A) == A[:,::-1,...])
True

python矩阵水平镜像

原文：http://www.cnblogs.com/haiyang21/p/7499660.html