> Le 28 août 2018 à 14:43, Ab Ab a écrit :
>
> because I get this error AttributeError: type object
> 'MiniBatchIteratorConstantBatchSize' has no attribute 'dataset'
>
This error is probably because MiniBatchIteratorConstantBatchSize doesn't
properly support pickle, but there could be
because I get this error AttributeError: type object
'MiniBatchIteratorConstantBatchSize' has no attribute 'dataset'
I have searched a lot but I could not find any better way to predict with
new dataset on a saved model in python.
On Tue, Aug 28, 2018 at 2:13 PM Arnaud Bergeron wrote:
> Why
Why are you trying to do this?
> from MiniBatchIteratorConstantBatchSize import dataset
This cannot work with the code you posted since
MiniBatchIteratorConstantBatchSize is not a module. That has nothing to to
with Theano, but rather is due to how python works.
Arnaud
--
---
You