tensorflow常见错误

a = tf.placeholder(dtype=tf.int32, shape=[2])
print(a)
a = tf.reduce_max(a)
print(a)
with tf.Session() as sess:
    print(sess.run(a, feed_dict={a:[5,10]}))

out:
Tensor("Placeholder:0", shape=(2,), dtype=int32)
Tensor("Max:0", shape=(), dtype=int32)
Traceback (most recent call last):
  File "/home/hdj/yk/WEBQA/ceshi.py", line 16, in <module>
    print(sess.run(a, feed_dict={a: [5,10]}))
  File "/home/hdj/anaconda3/envs/ky/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 905, in run
    run_metadata_ptr)
  File "/home/hdj/anaconda3/envs/ky/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1116, in _run
    str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (2,) for Tensor 'Max:0', which has shape '()'

 

a = tf.placeholder(dtype=tf.int32, shape=[])
b = a + a
b = b + b


with tf.Session() as sess:
    print(sess.run(b, feed_dict={a:2}))

out:
8

 

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值