tensorflow - 对于占位符的形状，[]、[None]、None 和 () 有什么区别？

Question

我见过使用 [] 的代码片段, [None] , None或 ()作为 placeholder 的形状， 那是

x = tf.placeholder(..., shape=[], ...)
y = tf.placeholder(..., shape=[None], ...)
z = tf.placeholder(..., shape=None, ...) 
w = tf.placeholder(..., shape=(), ...)

这些有什么区别？

Answer 1

TensorFlow 使用数组而不是元组。它将元组转换为数组。因此[]和 ()是等价的。

现在，考虑这个代码示例:

x = tf.placeholder(dtype=tf.int32, shape=[], name="foo1")
y = tf.placeholder(dtype=tf.int32, shape=[None], name="foo2")
z = tf.placeholder(dtype=tf.int32, shape=None, name="foo3")

val1 = np.array((1, 2, 3))
val2 = 45

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    #print(sess.run(x, feed_dict = {x: val1}))  # Fails
    print(sess.run(y, feed_dict = {y: val1}))
    print(sess.run(z, feed_dict = {z: val1}))

    print(sess.run(x, feed_dict = {x: val2}))
    #print(sess.run(y, feed_dict = {y: val2}))  # Fails
    print(sess.run(z, feed_dict = {z: val2}))

可以看出，占位符 [] shape 直接采用单个标量值。带有 [None] 的占位符shape 采用一维数组和占位符 None shape 可以在计算发生时取任何值。