tensorflow 学习随记

tensorflow 中 placeholder占位符在 feed_dict填入时不接受Tensor objec，可以传入scalars, strings, lists, numpy ndarrays, or TensorHandles

错误如下：

The value of a feed cannot be a tf.Tensor object. Acceptable feed values include Python scalars, strings, lists, numpy ndarrays, or TensorHandles

import tensorflow as tf
import numpy as np

a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)

v = [[1,2], [4,5]]

c = tf.constant([[1.0,2.0], [3.0,4.0]], dtype=tf.float32, name="c")
d = tf.Variable([[1.0,2.0], [3.0,4.0]], name="d")

op = tf.add(a,b)

init_op = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init_op)
    print("op = ", sess.run(op, feed_dict={a: v, b:v}))
    # print("op = ", sess.run(op, feed_dict={a: c, b: c}))  #error
    # print("op = ", sess.run(op, feed_dict={a: d, b: d}))  #error