Hello Everyone:
I am working on the code train.py given
at https://github.com/glample/tagger. My intentions are to implement batch
mode in line 214 of train.py code (as follows):
seq_inp = T.ftensor3('seq_matrix')
n_steps=seq_inp.shape[0]
batch_cost, updates=theano.scan(f_train, sequence=[seq_inp],
n_steps=n_steps)
Here seq_inp is the mini-batch data and is obtained by appending 32 data
samples of input defined in line 213 of train.py code. However, when i
execute the above portion of code inside train.py I get an error saying
'expected an array like object but found a variable'.
Any lead as to how to implement batch mode in train.py. Thanks in advance!!
Regards
Deepak
--
---
You received this message because you are subscribed to the Google Groups
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
