python - np.squeeze() 用于实现成本函数和梯度

Question

以下是基于 Coursera 深度学习类(class)计算成本函数和梯度以便对图像进行分类的代码。

计算成本如下

cost = -np.sum(Y*np.log(A) + (1-Y)*np.log(1-A)) / m 

cost.shape 是

()

那么下面操作的目的是什么

cost = np.squeeze(cost)

在函数中

def propagate(w, b, X, Y):
    """
    Implement the cost function and its gradient for the propagation

    Arguments:
    w -- weights, a numpy array of size (num_px * num_px * 3, 1)
    b -- bias, a scalar
    X -- data of size (num_px * num_px * 3, number of examples)
    Y -- true "label" vector (containing 0 if non-cat, 1 if cat) of size (1, number of examples)

    Return:
    cost -- negative log-likelihood cost for logistic regression
    dw -- gradient of the loss with respect to w, thus same shape as w
    db -- gradient of the loss with respect to b, thus same shape as b

    """
    m = X.shape[1]

    # FORWARD PROPAGATION (FROM X TO COST)
    A = sigmoid(np.dot(w.T, X) + b)          # compute activation
    cost = -np.sum(Y*np.log(A) + (1-Y)*np.log(1-A)) / m      # compute cost

    # BACKWARD PROPAGATION (TO FIND GRAD)
    dw = np.dot(X, (A-Y).T) / m
    db = np.sum(A-Y) / m

    assert(dw.shape == w.shape)
    assert(db.dtype == float)
    cost = np.squeeze(cost)
    assert(cost.shape == ())

    grads = {"dw": dw,
             "db": db}

    return grads, cost

Answer 1

np.squeeze用于移除numpy.ndarray中带有Singleton元素的轴。例如，如果你有一个形状为 (n,m,1,p) 的 numpy 数组 a，那么 np.squeeze(a)将使形状成为 (n,m,p)，减少第三个轴，因为它只有一个元素。

这里，cost 应该是一个单一的值。虽然它是 () 形状的 np.ndarray，但在计算自身之后，一个额外的步骤 np.squeeze(a) 被明确地用于确保如果它确实包含任何冗余轴，则将其删除。