Select to view content in your preferred language

Fail to classify pixels using deep learning with GPU

1194
4
06-22-2023 05:55 AM
XISHI
by
New Contributor

When I run the toolbox "Classify pixels using deep learning" with the CPU, everything seems fine, except that it runs extremely slow. So I tried to run it with the GPU and got multiple failures::

ExecuteError: ERROR 999999: Something unexpected caused the tool to fail. Contact Esri Technical Support (http://esriurl.com/support) to Report a Bug, and refer to the error help for potential solutions or workarounds.
Parallel processing job timed out [Failed to generate table]
Parallel processing job timed out [Failed to generate table]
Failed to execute (DetectObjectsUsingDeepLearning).

 

The parameters and environments were set as below:

XISHI_3-1687437672989.png

XISHI_4-1687437682490.png

Then I further try it in the Python command line with:

with arcpy.EnvManager(processorType="GPU"):
out_classified_raster = arcpy.ia.ClassifyPixelsUsingDeepLearning("setnul_raste", r"E:\Z_Phd_Other_stuff\2023_06_21_jx\jx\MyProject\model_unet2\model_unet2.dlpk", "padding 0;batch_size 32;predict_background False;test_time_augmentation False;tile_size 224", "PROCESS_AS_MOSAICKED_IMAGE", None); out_classified_raster.save(r"E:\Z_Phd_Other_stuff\2023_06_21_jx\jx\MyProject\MyProject.gdb\setnul_raste_ClassifyPixelsU3")

The same error occurred:

Traceback (most recent call last):
File "<string>", line 2, in <module>
File "C:\Program Files\ArcGIS\Pro\Resources\ArcPy\arcpy\ia\Functions.py", line 2206, in DetectObjectsUsingDeepLearning
return Wrapper(
File "C:\Program Files\ArcGIS\Pro\Resources\ArcPy\arcpy\sa\Utils.py", line 55, in swapper
result = wrapper(*args, **kwargs)
File "C:\Program Files\ArcGIS\Pro\Resources\ArcPy\arcpy\ia\Functions.py", line 2195, in Wrapper
result = arcpy.gp.DetectObjectsUsingDeepLearning_ia(
File "C:\Program Files\ArcGIS\Pro\Resources\ArcPy\arcpy\geoprocessing\_base.py", line 512, in <lambda>
return lambda *args: val(*gp_fixargs(args, True))
arcgisscripting.ExecuteError: ERROR 999999: Something unexpected caused the tool to fail. Contact Esri Technical Support (http://esriurl.com/support) to Report a Bug, and refer to the error help for potential solutions or workarounds.
Parallel processing job timed out [Failed to generate table]
Parallel processing job timed out [Failed to generate table]
Failed to execute (DetectObjectsUsingDeepLearning).

 

My PC has an AMD 7950X CPU and RTX 4090 (GPU0) and the version of ArcGIS Pro is 3.0.1. Is there any solution or suggestion?

XISHI_6-1687438453724.png

 

XISHI_5-1687438356685.png

 

0 Kudos
4 Replies
XISHI
by
New Contributor

Or anything I missed?

0 Kudos
JesseCloutier
Esri Community Manager

@XISHI, I've moved this post from our Community Feedback area to the ArcGIS Pro Questions Board, where it's more likely to be seen and responded to by members with relevant expertise. All the best!

Jesse Cloutier
Community Manager, Engagement & Content
0 Kudos
PavanYadav
Esri Regular Contributor

@XISHI 

Have you been able to fix it? Your nividia GPU should work. just for a test can you please try a smaller batch size e.g. 2 or 4? Are you running the tool within ArcGIS Pro or from a script?

Cheers!

Pavan Yadav | Product Engineer - Imagery and AI
Esri | 380 New York | Redlands, 92373 | USA

https://www.linkedin.com/in/pavan-yadav-1846606/ 

 

Pavan Yadav
Product Engineer at Esri
AI for Imagery
Connect with me on LinkedIn!
Contact Esri Support Services
0 Kudos
Kaifichomani
New Contributor

Same problem here and not fixed yet. 
I used ArcGIS pro 3.4 and classify pixels using deep learning. Training the model was successful but when I choose to test the same model, the GPU is not working. I have RTX4060.

0 Kudos