TypeError: Can not convert a ndarray into a Tensor or Operation.

最新推荐文章于 2020-11-21 10:32:11 发布

LoveWeeknd

最新推荐文章于 2020-11-21 10:32:11 发布

阅读量2.7k

点赞数 1

分类专栏： Tensorflow

本文链接：https://blog.csdn.net/oMoDao1/article/details/81193220

版权

Tensorflow 专栏收录该内容

24 篇文章 3 订阅

订阅专栏

import tensorflow as tf
from numpy.random import RandomState

batch_size = 8
# x = tf.constant([[0.7,0.2]], dtype=tf.float32)
x = tf.placeholder(dtype=tf.float32, shape=(1,2))
w1 = tf.Variable(tf.random_normal([2,3], dtype=tf.float32, name='w1', seed=1))
w2 = tf.Variable(tf.random_normal([3,1], dtype=tf.float32, name='w2', seed=1))
a = tf.matmul(x, w1)
y = tf.matmul(a, w2)
rdm = RandomState(1)
X = rdm.rand(10, 2)
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    print(sess.run(y, feed_dict={x:[[0.5,0.8]]}))
    print(sess.run(X))

运行结果：TypeError: Can not convert a ndarray into a Tensor or Operation.

原因：print(sess.run(X))，由于X不是tensor，所以使用sess.run(X)就会出错，改用printf(X)即可