Issues with i.segment.uspo

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

Issues with i.segment.uspo

Alexander, Daniel (PG)

To whom this may concern,


I am currently trying to use the i.segment.uspo tool for obia on a high resolution data set. However I keep recieving the following error:


ValueError: max() arg is an empty sequence


I am carrying out the classification in the Grass UI. Could you provide me with any guidance, or possibly redirect me to soem resources?


Many thanks,

Dan


_______________________________________________
grass-web mailing list
[hidden email]
https://lists.osgeo.org/mailman/listinfo/grass-web
Reply | Threaded
Open this post in threaded view
|

Re: Issues with i.segment.uspo

Markus Neteler
Dan,

Alexander, Daniel (PG) <[hidden email]> schrieb am Fr., 26. Okt. 2018, 13:04:

To whom this may concern,


I am currently trying to use the i.segment.uspo tool for obia on a high resolution data set. However I keep recieving the following error:


ValueError: max() arg is an empty sequence


I am carrying out the classification in the Grass UI. Could you provide me with any guidance, or possibly redirect me to soem resources?


Many thanks,

Dan


So you use a recent version? Just to be sure the we speak about the current i.segment.uspo.

Best,
Markus


_______________________________________________
grass-web mailing list
[hidden email]
https://lists.osgeo.org/mailman/listinfo/grass-web
Reply | Threaded
Open this post in threaded view
|

Re: Issues with i.segment.uspo

Moritz Lennert
Hi Dan,

On 26/10/18 13:06, Markus Neteler wrote:

> Dan,
>
> Alexander, Daniel (PG) <[hidden email]
> <mailto:[hidden email]>> schrieb am Fr., 26. Okt. 2018,
> 13:04:
>
>     To whom this may concern,
>
>
>     I am currently trying to use the i.segment.uspo tool for obia on a
>     high resolution data set. However I keep recieving the following error:
>
>
>     ValueError: max() arg is an empty sequence
>
>
>     I am carrying out the classification in the Grass UI. Could you
>     provide me with any guidance, or possibly redirect me to soem resources?
>
>
>     Many thanks,
>
>     Dan
>
>
> So you use a recent version? Just to be sure the we speak about the
> current i.segment.uspo.

I just (1 min ago) committed a fix to i.segment.uspo which should handle
this case. Please reinstall the module using g.extension. If you work
with MS Windows, you will have to wait for it a bit to become available
(max 24h).

This said, this error generally happens when one of the segmentation
levels asked for leads to a result with one single segment. This depends
on your image, the threshold range you are testing, but also the region
you are working with.

It would help if you gave us some info about the data:

- output of g.region -p
- output of g.region region=OneOfYourTestRegions -up
- output of r.info on one of the bands you are using
- the call you used for i.segment.uspo - you should be able to find the
command line used in the GUI "Command console" by using the up arrow -
or once you have filled in all the fields in the module GUI, just click
on the "Copy" button to copy the command line to the clipboard.

Moritz


_______________________________________________
grass-web mailing list
[hidden email]
https://lists.osgeo.org/mailman/listinfo/grass-web