Detect Objects Using Deep Learning Error: Python Raster Function's .vectorize() method returned nothing

1146
1
Jump to solution
04-14-2021 01:56 AM
Labels (2)
向宁焦
New Contributor

Error appers when I use "Detect Objects Using Deep Learning" in ArcGIS Pro, the model is usa_building_footprints.dlpk which trained by ArcGIS Pro 2.7.3.

向宁焦_0-1618390244486.png

Expected behavior
How to make the model work.

Platform (please complete the following information):

  • OS: Win10
  • ArcGIS Pro Version: 2.7.3
  • GPU: NVIDIA Quadro P620, 4GB GPU Memory
  • Test Image Size: 936MB

向宁焦_1-1618390311194.png

 

 

Tags (1)
0 Kudos
1 Solution

Accepted Solutions
Tim_McGinnes
Occasional Contributor III

It is the error directly above that is causing the problem: RuntimeError: CUDA out of memory.

This means that all the dedicated memory on your graphics card is being used up while running the Detect Objects tool. The Batch Size parameter controls how many image segments are sent to the graphics card at once for detection. You will need to reduce the Batch Size parameter in the tool until it runs without error. I suggest setting it to 1 or 2 to begin with, and you can increase it later if required. See attached screenshot to see where the Batch Size parameter can be found.

View solution in original post

1 Reply
Tim_McGinnes
Occasional Contributor III

It is the error directly above that is causing the problem: RuntimeError: CUDA out of memory.

This means that all the dedicated memory on your graphics card is being used up while running the Detect Objects tool. The Batch Size parameter controls how many image segments are sent to the graphics card at once for detection. You will need to reduce the Batch Size parameter in the tool until it runs without error. I suggest setting it to 1 or 2 to begin with, and you can increase it later if required. See attached screenshot to see where the Batch Size parameter can be found.