tf.placeholder(dtype, shape=None, name=None)python
placeholder,佔位符,在tensorflow中相似於函數參數,運行時必須傳入值。dom
- dtype:數據類型。經常使用的是tf.float32,tf.float64等數值類型。
- shape:數據形狀。默認是None,就是一維值,也能夠是多維,好比[2,3], [None, 3]表示列是3,行不定。
- name:名稱。
代碼片斷-1(計算3*4=12)函數
-
- import tensorflow as tf
- import numpy as np
-
- 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:[3.], input2: [4.]})
代碼片斷-2(計算矩陣相乘,x*x)spa
-
- import tensorflow as tf
- import numpy as np
-
- x = tf.placeholder(tf.float32, shape=(1024, 1024))
- y = tf.matmul(x, x)
-
- with tf.Session() as sess:
- rand_array = np.random.rand(1024, 1024)
- print(sess.run(y, feed_dict={x: rand_array}))