placeholder函數至關於一個佔位符,tf.placeholder(dtype, shape=None, name=None)函數
input1 = tf.placeholder(tf.float32) input2 = tf.placeholder(tf.float32) output = tf.multiply(input1,input2) with tf.Session() as sess: print(sess.run(output,feed_dict={input1:[7.],input2:[2.]}))#[14.]