Deep Learning for land classification Error

4301
16
03-23-2021 06:55 PM
Labels (1)
SherminHo
New Contributor II

Dear Community, 

attempted to classify pixels using deep learning by applying the Land Cover Classification dlpk.

However, an error returned: Error 999999

SherminHo_0-1616550831326.png

is there a way around this? 

 

Thanks

0 Kudos
16 Replies
SarahPC
New Contributor III

I actually had the same error to following with interest.

0 Kudos
Tim_McGinnes
Occasional Contributor III

Can you provide some more information to assist with diagnosing the problem -

- ArcGIS Pro version & how you installed the deep learning components

- Screenshot of the Messages in the geoprocessing output (it's down the bottom)

- Information on the input raster you are using - Type, Bands, Bits per Pixel, Columns, Rows, Coordinate System etc.

0 Kudos
SherminHo
New Contributor II

Hi Tim, 

Thanks for responding.

I'm currently on ArcGIS Pro 2.7.2. 

Installed the deep learning components by using the deep learning installer: 

https://github.com/Esri/deep-learning-frameworks/blob/master/README.md?rmedium=links_esri_com_b_d&rs...

Once installed, I ran the model again but was unable to read the dlpk. I then attempted to reload the deep learning frameworks manually by following the steps in this link:- pls also see attached for the python cmd prompt i used

https://github.com/Esri/deep-learning-frameworks/blob/master/install-deep-learning-frameworks-manual...

As for the information on the input raster, I was trying out with Multispectral Landsat imagery found on Living Atlas: https://landsat2.arcgis.com/arcgis/services/Landsat/MS/ImageServer

SherminHo_0-1616556695889.png

SherminHo_1-1616556710400.png

 

0 Kudos
Tim_McGinnes
Occasional Contributor III

By default the Landsat service will show you a 3 band combination, but the deep learning model expects 7 bands. In the properties of the Landsat service under Processing Templates, you need to set the Processing Template to None. Worked for me ok once I did that. You should probably set your required extent in the environment variables as well.

SherminHo
New Contributor II

Hi Tim, 

Thanks for the tip. unfortunately, even after setting the processing template to None, and trying out on the extent in the example you have shared,  i'm still receiving the same error message: 

SherminHo_0-1616569919313.png

 

0 Kudos
Tim_McGinnes
Occasional Contributor III

Well it's a slightly different error this time. My only suggestion now would be to go back to using the default Python environment (arcgispro-py3). What did you mean when you said it was "unable to read the dlpk"? I am also on Pro 2.7.2, and used the deep learning framework from the installer and using the default environment.

0 Kudos
SherminHo
New Contributor II

Thanks for the advice Tim

0 Kudos
by Anonymous User
Not applicable

Hi,

Yes you need to set the processing template to None. 

Looking at the error It seems to me that you are trying to apply the sentinel 2 Landcover model on a Landsat 8 Imagery. I recommend you to confirm the model you are trying to use.


This model works with Landsat 8 Imagery https://www.arcgis.com/home/item.html?id=e732ee81a9c14c238a14df554a8e3225

and this model works with Sentinel 2 Imagery https://www.arcgis.com/home/item.html?id=afd124844ba84da69c2c533d4af10a58

 

Thanks,

Sandeep

SherminHo
New Contributor II

Hi Sandeep, 

Thanks for spotting the error. will rerun the model and update again 🙂

0 Kudos