np.random.seed()产生随机数规则

np.random.seed()产生随机数规则

import numpy as np
if __name__ == '__main__':
    np.random.seed(1)
    L1 = np.random.randn(1, 3)
    np.random.seed(1)
    L2 = np.random.randn(1, 3)
    np.random.seed(2)
    L3 = np.random.randn(1, 3)

    L4 = np.random.randn(1, 3)
    np.random.seed(2)
    L5 = np.random.randn(1, 3)
    print(L1)
    print(L2)
    print(L3)
    print(L4)
    print(L5)

得出结果

[[ 1.62434536 -0.61175641 -0.52817175]]
[[ 1.62434536 -0.61175641 -0.52817175]]
[[-0.41675785 -0.05626683 -2.1361961 ]]
[[ 1.64027081 -1.79343559 -0.84174737]]
[[-0.41675785 -0.05626683 -2.1361961 ]]

结论:产生随机数前，调用参数相同的seed()，则得出的随机数相同，否则不同