L_model_backward.py

def L_model_backward(AL, Y, caches):

    grads = {}
    L = len(caches) # the number of layers
    m = AL.shape[1]
    Y = Y.reshape(AL.shape) # after this line, Y is the same shape as AL

    dAL = dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))

    current_cache = caches[-1]
    grads["dA" + str(L)], grads["dW" + str(L)], grads["db" + str(L)] = linear_backward(sigmoid_backward(dAL, current_cache[1]), current_cache[0])
    
    for l in reversed(range(L-1)):
        current_cache = caches[l]
        dA_prev_temp, dW_temp, db_temp = linear_backward(sigmoid_backward(dAL, current_cache[1]), current_cache[0])
        grads["dA" + str(l + 1)] = dA_prev_temp
        grads["dW" + str(l + 1)] = dW_temp
        grads["db" + str(l + 1)] = db_temp
        
    return grads