[英]tensorflow InvalidArgumentError: You must feed a value for placeholder tensor with dtype float
[英]Tensorflow: InvalidArgumentError: You must feed a value for placeholder tensor 'yy' with dtype int32
import tensorflow as tf
y_hat = tf.constant(36, name='y_hat') # Define y_hat constant. Set to 36.
yy = tf.placeholder(tf.int32, shape=[])
loss = tf.Variable((yy - y_hat)**2, name='loss') # Create a variable for the loss
init = tf.global_variables_initializer()
with tf.Session() as session:
session.run(tf.global_variables_initializer(), feed_dict = {yy: 39})
print(session.run(loss, feed_dict={yy: 39}))
作為Tensorflow的新手,我很難理解在這個框架中如何管理占位符。
如果我第一次運行上面的代碼,它將返回9(正確的值)。 但是如果我在同一個jupyter會話中再次運行它,我會得到以下錯誤。 就好像我使用“with”來關閉會話一樣,全局變量(在本例中為占位符)沒有得到清理
堆棧跟蹤:
InvalidArgumentError: You must feed a value for placeholder tensor 'yy' with dtype int32
[[Node: yy = Placeholder[dtype=DT_INT32, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op 'yy', defined at:
File "/opt/conda/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/opt/conda/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
知道發生了什么以及如何解決它? 謝謝
在import tensorflow as tf
右下方添加行tf.reset_default_graph()
import tensorflow as tf
,這樣每次運行代碼時都會重置張量流圖。 那你就不會得到這個錯誤。
順便說一下,您並不需要將loss
指定為變量。 你可以跑
import tensorflow as tf
y_hat = tf.constant(36, name='y_hat')
yy = tf.placeholder(tf.int32, shape=[])
loss = (yy - y_hat)**2
with tf.Session() as session:
print(session.run(loss, feed_dict={yy: 39}))
上面的代碼打印9。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.