You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Dec 19, 2023. It is now read-only.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
我在debug到每个类的call函数内,发现Inputs.shape的结果是(None,30,9), 9是我这里features维度。Inputs的第一维大小是None。我查了网上说因为batch的设置,在static时第一维是不确定的。但是可以通过tf.shape(Inputs)来查询dynamic的真正shape。但是tf.shape(Inputs)返回一个tensor,好像也没有一个办法去获取这个tensor的数据?我用_tf.compat.v1.InteractiveSession(), 再用tesnor.eval(),好像也不行。Model.fit()的时候是不是已经开始了一个session啊?我应该怎么或者Inputs第一维的真正值呢? 谢谢
Beta Was this translation helpful? Give feedback.
All reactions