Hi,
I find the module ObjectRadiometricStatistics very useful for vector
classification. But we cannot use it through QGIS. I have already written
an XML file for this module with OTB 6.4.0 and in QGIS 2.18. And this
algorithm works properly. But with QGIS 3.4 and as OTB is become an
external
Hi,
I have successfully set up a qgis envivronment in an external python
console (spyder) but I cannot use OTB algorithms that are listed in QGIS
geoprocessing tool box. I have checked with processing.alglist() but
processings from external providers (OTB, LAS...) are missing.
This is my code :
Hi,
It seems that your Train samples file does not have 14 features to use for
the classifier. This number of features must be equal to the number of
features computed in the XML file, though the module generates variance and
mean for each feature.
Le jeu. 13 déc. 2018 à 09:01, Friederike
idge: Intel Corporation Xeon 5600 Series Integrated Memory
Controller Channel 2 Rank (rev 02)
3f:06.3 Host bridge: Intel Corporation Xeon 5600 Series Integrated Memory
Controller Channel 2 Thermal Control (rev 02)
Le mar. 20 nov. 2018 à 15:23, Etienne MAHE a écrit :
> About the options
xes, I will continue to use 6.4.0.
Best regards,
Etienne MAHE
Le mercredi 4 juillet 2018 11:42:34 UTC+2, Etienne MAHE a écrit :
>
> Hi,
>
> Since OTB 6.6.0-Win64 release, the app Train Vector Classifier seems to
> have a bug when running with libSVM classifier and espec
Just to finish, there is no issue, neither with other train vector
classifier (such as random forest or knn), nor with vector classifier.
Le sam. 10 nov. 2018 21:21, Etienne MAHE a écrit :
> It is only for libsvm train vector classifier. When the option parameters
> optimization is e
ool completed fine with the
> parameters optimization enabled, is it the trainer or the train vector
> classifier that has a bug or the vector classifier where the bug happens?
>
> On Thursday, November 8, 2018 at 2:58:39 PM UTC-6, Etienne MAHE wrote:
>>
>> Hi,
>&g
My mistake, it is the compute image second order statistics.
Le jeu. 8 nov. 2018 21:58, Etienne MAHE a écrit :
> Hi,
>
> Yes, if you previousely use the module Compute Image Order second
> statistics to generate an xml file, the number of features must match to
> the
Hi,
Yes, if you previousely use the module Compute Image Order second
statistics to generate an xml file, the number of features must match to
the number of bands of the image used for the classifications. From my
experience for classification of aerial photos (rgb and nir), only mean and
medians