技術標籤：深度學習

附錄： 吳恩達深度學習中，simoid， relu反相求導程式碼， 後期應用時方便參考

其中 dA 如下：

dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL)) # derivative of cost with respect to AL

cache： 儲存A_pre, w_l, b_l. 即A _pre為第l層的輸入。

1. sigmoid 求導

def sigmoid_backward(dA, cache):
    """
    Implement the backward propagation for a single SIGMOID unit.
    
    Arguments:
    dA -- post-activation gradient, of any shape
    cache -- 'Z' where we store for computing backward propagation efficiently

    Returns:
    dZ -- Gradient of the cost with respect to Z
    """
 

    #
    Z = cache
    #
    s = 1 / (1 + np.exp(-Z))
    #
    dZ = dA * s * (1 - s)   ## 這裡為什麼乘dA， 沒有懂
    print("sigmoid", dA.shape, s.shape, dZ.shape)
    print(dA, s, dZ)
    assert (dZ.shape == Z.shape)
    #
    return dZ

2. relu求導

def relu_backward(dA, cache):
    """
    Implement the backward propagation for a single RELU unit.

    Arguments:
    dA -- post-activation gradient, of any shape
    cache -- 'Z' where we store for computing backward propagation efficiently

    Returns:
    dZ -- Gradient of the cost with respect to Z
    """
 

    #
    Z = cache
    dZ = np.array(dA, copy=True)  # just converting dz to a correct object.  --這裡沒太懂
    # When z <= 0, you should set dz to 0 as well.
    dZ[Z <= 0] = 0
    assert (dZ.shape == Z.shape)
    #
    return dZ