Multiple input model help

Dear all,

i would like to know if it is possible to create a deep learning model in deep learning studio with multiple input?

Yes DLS supports multiple input and single output model.
You can select as many as feature as inputport0 in the Data tab.

Regards
Rajat

Dear Rajat,

Thank you for your answer.Actually i am working on a data set that contain two image for each item.
i am not sure how to input it into DLS. Is there any example for that?

Best Regards,

Ok if you need both the images in a single row then you can save them as a numpy file and work on them as a 3-D image.
This article might help you on how to make numpy files and use them with DLS.
https://towardsdatascience.com/recognition-of-action-in-video-with-deep-learning-studio-9ffad2283080

Regards
Rajat

Unfortunately I get the error 410 trying to open the link “Recognition of Action with Deep Learning Studio”.

Is there any documentation, how a numpy file has to be structured, that DLS can import it as DataSource. Or is there any documentation for the different importable datatypes at all? What can be imported and how does the import file has to be formatted?
I know, there is the meta.json file, which tells DLS what to import. But I can’t find any documentation for the parameters in that file and what will be accepted by DLS.
I only find the very simple importing tutorials with very simple data-structure. But that can’t be all?!?!
Best regards
Matthias

Hi you need to first store all the numpy file with “.npz” format.
And store all the numpy files similar as we store image dataset.

1 Like