The ArcGIS Pro 2.8.1 patch does seem to resolve this issue.
Wanting to try out some of the new deep learning tools in Pro 2.8. I have a clean install of 2.8, cloned Python environment and the deep learning modules installed by "conda install deep-learning-essentials".
I can successfully run the deep learning tools with CPU specified in the environment variables. But when I choose GPU I get an error box popup: "ArcGIS Pro has experienced a fatal authorization error and must close". Screenshot attached showing error and messages when running the Detect Objects tool.
I have ArcGIS Pro 2.8 Advanced and the Image Analyst extension licensed as a named user through ArcGIS Online. The same thing is occurring on two different machines, desktop with 5Gb Quadro P2000 and laptop with 8Gb GeForce RTX 2080. Both machines on Windows 10.
Am I just too quick off the mark trying to do deep learning in Pro 2.8?
Deep Learning Essentials :: Anaconda.org
Can you check the 2nd link versus your download to make sure the version for 2.8 was installed.
In the last link, it appears that the install instructions for 2.8 aren't up yet.
Deep learning frequently asked questions—ArcGIS Pro | Documentation
In case I missed something.
Further investigation shows these tools have the error when using GPU:
These tools work without problems when using GPU:
All the tools above work without problems when using CPU.
Additionally, I can perform inferencing with a Change Detection model using the GPU when using a Jupyter Notebook.
@Tim_McGinnes you might want to look at the first issue at...
Issues · Esri/deep-learning-frameworks (github.com)
It isn't your gpu, however, it provides background.
You might be advised to file an Issue there if you haven't done one through Tech Support yet.
Issue logged at the Esri Deep Learning Frameworks GitHub site, and someone else has independently confirmed the error: https://github.com/Esri/deep-learning-frameworks/issues/19
Adding in some Esri folks for assistance: @VinayViswambharan, @SandeepKumar1
Hi,
This issue is being addressed and will be available in the next update. Apologies and Thank you for your patience
Hi All,
Any updates on this? I am also having the same issue with 2.8.
I see this particular error dialog when executing "Classify Objects Using Deep Learning" from both GUI and arcpy function. It creates an empty output feature class. Please advise if we need to reinstall 2.7 from 2.8 to use deep learning tools.
Esri have advised that it will be fixed in the Pro 2.8.1 update. I have gone back to 2.7 until then.
As for the 2.8.1 release date: When is ArcGIS Pro 2.8.1 expected to drop?
Hi Tim.
Thanks for the quick response. I think I will need to revert back to 2.7 as well. It is unfortunate/headache to revert back to 2.7 with python downgrades after all the improvements and bug fixes were announced.
Hi Shingo-Ikeda,
Apologize for the inconvenience. The 2.8.1 patch is planned as a early update and should be out sooner than later ...in the coming weeks.
Thanks for the update. I will look for the release and apply it as soon as it becomes available. In a meantime, I have reverted back to 2.7.4.
The ArcGIS Pro 2.8.1 patch does seem to resolve this issue.
Is anyone facing issue with "Classify objects using deep learning" in 2.8.1? The tools shows 100% run before the process is complete.
Hi S6,
Does the tool complete successfully for you? Just want to confirm it is just a progress bar issue. Thanks.
Hi S6,
The fix for Classify Objects has been fixed and will be in 2.8.2 which will be out soon.
Thanks for the update!
Could you specify the details of the bug that was fixed for the Classify Objects. I am running into some issues, but I am not sure if they are related.
Hello Shingo-Ikeda,
The Classify Objects tool was taking a long time to run for larger datasets. . The inference process is intensive but it should not take you many hours for a couple of thousand features. This has been fixed in 2.8.2. We are also looking into fixing an issue with the incorrect progress bar where it shows 100% complete when the tool is still running as well as varying results on different extent runs. That will be fixed shortly. If you are facing other issues please tell us your issue and we will look into it . Thanks.