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
I think this issue is caused by the auto variable format converting of python 3.
I use python 2, so when the self.D_stride is an "int", the self.D_stride/2 is also an "int", but in python 3, it will change to a float.
You may use int(.) function to convert the parameters into "int" compulsively or use "//".
This should solve the issue
padding=(
(tf.cast((self.D_stride-1)/2,tf.int32), tf.cast((self.D_stride-1)/2+1,tf.int32)),
(tf.cast((self.D_stride-1)/2,tf.int32), tf.cast((self.D_stride-1)/2+1,tf.int32))),
Thanks for the code @LeonLIU08 !
However when running the example I am getting the following error on this part:
Error:
TypeError: Value passed to parameter 'paddings' has DataType float32 not in list of allowed values: int32, int64
Any suggestions?
Running the latest Keras version
The text was updated successfully, but these errors were encountered: