topic Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."] in ArcGIS Pro Questions

ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

WernerBaak — Mon, 17 Aug 2020 15:13:00 GMT

Hey,

I have a problem when I try to export training data for deep learning. The error is "Labeled sample objects could not be saved for the run."

I have tried it with my data first, but as I couldn't manage to get to run it I went through the "Deep learning Tutorial - Assess Palm Tree Health" (Use Deep Learning to Assess Palm Tree Health | Learn ArcGIS ).

However I cannot export data even though I have tried all kind of "meta data formats" and "image formats".

I would appreciate any help.

PS: I am using ArcGIS Pro 2.6.0

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

FlorenciaPineiro — Thu, 03 Sep 2020 16:10:54 GMT

Hi Werner!

I have the same issue you comment. May somebody help us?

Thanks!

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

KoryKramer — Thu, 03 Sep 2020 18:17:29 GMT

I apologize that you're running into issues with this lesson. I recently reviewed something similar with a colleague so wanted to share what I think may be happening.

On this step:

what it is doing is having you try to save the training samples in a folder.

However, in ArcGIS Pro 2.6, what you should do instead of going to the project folder, browse into the project geodatabase and save the training samples there.

Then try to proceed with the lesson.

Does that work?

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

FlorenciaPineiro — Thu, 03 Sep 2020 21:14:36 GMT

Hi Kory,

Thanks for your reply. I wrote here and then I came back to Pro in orden to try something different. So, I followed what you indicates but I wasn´t sure if it was right because it hadn´t finished yet.

It works! Thanks for your help!

Regards,

Florencia

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

WernerBaak — Fri, 04 Sep 2020 09:54:59 GMT

Hey Kory!

Thanks. It works!

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

KoryKramer — Fri, 04 Sep 2020 12:49:57 GMT

Thank you for confirming. I checked with the teams that maintain that lesson and they confirmed that it will be corrected in the next update of the lesson.

Once again, sorry that you ran into the problem.

Cheers

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

jdetka — Tue, 01 Dec 2020 06:26:36 GMT

KoryKramer,
I think you are correct with one added step. I had to go into Project > Python Package Manager and change my project environment back to arcgispro-py3. Then I exited and returned to my project saving the labeled objects into the geodatabased like you mentioned.

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

Manish — Wed, 06 Jan 2021 08:25:15 GMT

With this data exported to ImageChips but deep learning model is not accepting the that. Input folder of deep learning tool is giving error. I am working on the same sample (https://learn.arcgis.com/en/projects/use-deep-learning-to-assess-palm-tree-health/) and arcgis pro 2.7.

Request for quick response

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

MartyRyan — Wed, 17 Feb 2021 17:07:58 GMT

I followed the advice above to save the labeled objects into the geodatabase rather than the folder. Also, my Python environment is arcgispro-py3 - I had already downloaded the deep learning libraries). Now in attempting to run the Train Deep Learning Model tool, it asks for "Input Training Data" - when I try to find the training data (previously saved in the gdb), I cannot find the gbd - only the Image Chips folder which contains two empty folders (images and labels) I cannot seem to establish a connection to the CoconutHealth database in the Import Training Data window.

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

TimVandeVoorde — Thu, 18 Feb 2021 13:03:31 GMT

I am also following the palm tree tutorial and there seems to be an issue when your system uses commas instead of points as decimal separator. The bounding boxes in the xml files in my image chips folder look like this:

The fast.ai library tries to convert these to float but fails:

ValueError: could not convert string to float: '345,70'
Failed to execute (TrainDeepLearningModel).

Also, it seems impossible to save the training samples themselves, not even in a geodatabase.

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

TimVandeVoorde — Thu, 18 Feb 2021 13:24:38 GMT

I was able to solve the "comma" problem by changing my windows settings (using . as decimal seperator). This solution is far from ideal, however, as this has an impact on other applications. The saving of the training features turned out to be a refresh problem, but still appears somewhat buggy.

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

SedaSALAP-AYCA — Tue, 06 Apr 2021 14:40:04 GMT

Unfortunately, exporting training data through the Image Classification tool is persistent in 2.7. The output folder is required as Folder, not Geodatabase therefore you can only save through the Labeled Objects tab.

Once you save your Labeled Objects as features under a geodatabase, you can dismiss the Image Classification window. From the Geoprocessing tools, open Export Training Data for Deep Learning and fill the required fields as in the image. You will have your ImageChips ready to train your model!

Hope this helps!

Happy training your model!

Best,

Seda

Re: ERROR: Image Classification --> Export Training Data ["Labeled sample objects could not be saved for the run."]

SaeedehMadani — Thu, 10 Jun 2021 14:42:38 GMT

Hi,

I creates a polygon feature class and started digitize my training sample and the name of the field like below

then I exported my training sample ,though it did not recognize the class value field but it runs successfully with a warning now that I want to Train Deep Learning Model it when I insert my output folder from previous step it gives this error and do not know what to do as I spend too much time on it but it still have this error:

ERROR 032659 updateParameters Error: Traceback (most recent call last):
File "c:\program files\arcgis\pro\Resources\ArcToolbox\toolboxes\Image Analyst Tools.tbx\TrainDeepLearningModel.tool\tool.script.validate.py", line 427, in <module>
File "c:\program files\arcgis\pro\Resources\ArcToolbox\toolboxes\Image Analyst Tools.tbx\TrainDeepLearningModel.tool\tool.script.validate.py", line 192, in updateParameters
backbone_list = training_model._supported_backbones()
File "C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\Lib\site-packages\arcgis\learn\models\_ssd.py", line 244, in _supported_backbones
return [*_resnet_family, *_densenet_family, *_vgg_family, models.mobilenet_v2.__name__]
NameError: name '_resnet_family' is not defined