|
Hi, First thing to know is that during TrainImagesClassifier, some parts of the processing are mono-threaded (only 1 CPU used). This is a design limitation. However, the multi-threaded parts of this application should be able to use all the CPUs available. About the memory consumption, the RAM parameter in the application should set the maximum RAM amount to be used. I think that in the case of TrainImagesClassifier, this setting is difficult to derive because it depends on the polygon density in your training/validation vector layer. If you use an other application that is more like an "image to
image" processing, you should see the expected behaviour more
clearly. Guillaume On 11/24/2017 11:23 AM, Hristo Nikolov
wrote:
--
--
-- Check the OTB FAQ at http://www.orfeo-toolbox.org/FAQ.html You received this message because you are subscribed to the Google Groups "otb-users" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/otb-users?hl=en --- You received this message because you are subscribed to the Google Groups "otb-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. |
- [otb-users] efficient use of hardware resources by OTB Hristo Nikolov
- Re: [otb-users] efficient use of hardware resources ... Guillaume Pasero
