alternative way of concatenating two LSTM cell about crnn-with-stn HOT 6 CLOSED

Can you please let me know about this?
here rnn2_merged = concatenate([rnn_2, rnn_2b])
the dimension of rnn_2 = (?, ?, 128)
and rnn_2b= (?, ?, 128)
is there anyway we can give the actual size to rnn_2 and rnn_rb rather than ?
Or because the lenght is varient it is not possible?

Thanks again.

You cannot set the specific dimension of rnn_2, two "? " depend on input dataset at the very beginning, First'?' presents the batch size, and the second is 1/8 of input image width.

from crnn-with-stn.

Keras is tensorflow-based, so you can use functions from tensorflow to concatenate two tensors together.

from crnn-with-stn.

Could you please share a link with me in which doing this?
I just want to make sure my revised code will be exactly the same as code here.

Thanks in advance:)

from crnn-with-stn.

Could you please share a link with me in which doing this?
I just want to make sure my revised code will be exactly the same as code here.

Thanks in advance:)

https://apimirror.com/tensorflow~python/tf/concat

Or you can look for concatenate function in Keras source code, as a reference.

from crnn-with-stn.

It did not help actually, Im trying to convert your code to CoreMl, but CoreMl does not support concatenate!
this guy changed his code vsyw/Keras-OpenFace#1 to change the channel to be able to do so.
Can you please have a look to see if it is doable on your code?

from crnn-with-stn.

Can you please let me know about this?
here rnn2_merged = concatenate([rnn_2, rnn_2b])
the dimension of rnn_2 = (?, ?, 128)
and rnn_2b= (?, ?, 128)
is there anyway we can give the actual size to rnn_2 and rnn_rb rather than ?
Or because the lenght is varient it is not possible?

Thanks again.

from crnn-with-stn.