張量流初始化變量錯誤

Question

眾所周知，有多種方法可以在 tensorflow 中初始化變量。 我嘗試了一些結合圖形定義的東西。 請參閱下面的代碼。

def Graph1a():
    g1 = tf.Graph()
    with g1.as_default() as g:
        matrix1 = tf.constant([[3., 3.]])
        matrix2 = tf.constant([[2.],[2.]])
        product = tf.matmul( matrix1, matrix2, name = "product")

    sess = tf.Session( graph = g )
    sess.run(tf.global_variables_initializer())
    return product

def Graph1b():
    g1 = tf.Graph()
    with g1.as_default() as g:
        matrix1 = tf.constant([[3., 3.]])
        matrix2 = tf.constant([[2.],[2.]])
        product = tf.matmul( matrix1, matrix2, name = "product")

    sess = tf.Session( graph = g )
    sess.run(tf.initialize_all_variables())
    return product

def Graph1c():
    g1 = tf.Graph()
    with g1.as_default() as g:
        matrix1 = tf.constant([[3., 3.]])
        matrix2 = tf.constant([[2.],[2.]])
        product = tf.matmul( matrix1, matrix2, name = "product")

    with tf.Session( graph = g ) as sess:
        tf.global_variables_initializer().run()
        return product

為什么Graph1a()和Graph1b()不會返回產品，而Graph1c()呢？ 我認為這些陳述是等效的。

Answer 1

問題是global_variables_initializer需要與與會話相同的圖相關聯。 在Graph1c發生這種情況是因為global_variables_initializer在會話的 with 語句的范圍內。 為了讓Graph1a工作，它需要像這樣重寫

def Graph1a():
    g1 = tf.Graph()
    with g1.as_default() as g:
        matrix1 = tf.constant([[3., 3.]])
        matrix2 = tf.constant([[2.],[2.]])
        product = tf.matmul( matrix1, matrix2, name = "product")
        init_op = tf.global_variables_initializer()

    sess = tf.Session( graph = g )
    sess.run(init_op)
    return product