Deep learning frequently asked questions

Find answers to common questions about deep learning.

• What license do I need for the deep learning tools?

• Do I have to install all the deep learning libraries to run the deep learning tools?

• I have other versions of deep learning libraries installed. Will they work with the current version of ArcGIS AllSource?

• What are the GPU requirements for running deep learning tools?

• Can geoprocessing tools use multiple GPUs on a single machine?

• Which tools support multiple GPUs?

• I have an older GPU that is incompatible with the software, or I have low GPU memory. What are the requirements?

• How do you monitor how much GPU memory is being used?

• Why is my CUDA GPU not working with my ArcGIS deep learning tools?

• How can I speed up the inferencing tools?

• Why am I seeing conda or jupyter notebook not recognized as internal or external command when trying to install the libraries manually?

• What do I do if I see a Conda broken package error, or a verification error when trying to install libraries manually?

• After training, how do I know how well my model has performed?

• After running inferencing tools, how do I know how well my model performed?

• What library versions are required for ArcGIS Pro 3.3?

What license do I need for the deep learning tools?

All Image Analyst deep learning geoprocessing tools and the Label Objects for Deep Learning pane, which is used for deep learning with imagery in 2D, require the ArcGIS Image Analyst extension. Some of the tools are also available with the ArcGIS Spatial Analyst extension.

The Classification (Deep Learning) toolset and the Object Detection (Deep Learning) toolset both require the ArcGIS 3D Analyst extension.

The interactive Object Detection tool for imagery in a 3D scene requires either an ArcGIS Pro Advanced license or the ArcGIS Image Analyst extension.

Do I have to install all the deep learning libraries to run the deep learning tools?

Yes, you need to follow the instructions listed in Install deep learning frameworks for ArcGIS.

I have other versions of deep learning libraries installed. Will they work with the current version of ArcGIS AllSource?

No, each version of ArcGIS AllSource requires specific versions of the deep learning libraries. You must uninstall existing packages and libraries and install the versions listed in the installation instructions.

What are the GPU requirements for running deep learning tools?

The recommended VRAM for running training and inferencing deep learning tools in ArcGIS AllSource is 8GB. If you are only performing inferencing (detection or classification with a pretrained model), 4GB is the minimum required VRAM, but 8GB is recommended.

Can geoprocessing tools use multiple GPUs on a single machine?

Yes, geoprocessing tools that honor the GPU ID environment can use a specific GPU or multiple GPUs. To use all available GPUs, leave the GPU ID text box blank.

Which tools support multiple GPUs?

There are several geoprocessing tools that will use multiple GPUs on a single machine:

• The ArcGIS Image Analyst inferencing tools such as: Classify Objects Using Deep Learning, Classify Pixels Using Deep Learning, Detect Changes Using Deep Learning, and Detect Objects Using Deep Learning.
• The Train Deep Learning Model tool, when the Model Type parameter is set to one of the following options: ConnectNet, Feature classifier, MaskRCNN, Multi Task Road Extractor, Single Shot Detector, or U-Net.
• And the arcgis.learn models for training deep learning models.

I have an older GPU that is incompatible with the software, or I have low GPU memory. What are the requirements?

If you do not have the required 4 to 8GB VRAM, you can run most of the tools on the CPU, though the processing time will be longer.

The Detect Objects From Point Cloud Using Trained Model tool and the Train Point Cloud Object Detection Model tool do not support CPU processing; they can only run on the GPU. These tools return an error when the CPU is specified as the processor type.

How do you monitor how much GPU memory is being used?

Use nvidia-smi, which is a command line utility that is installed with NVIDIA drivers.

1. Open a Windows Command Prompt window.
2. Type nvidia-smi.
3. Press the Enter key.

   Note:

   If nvidia-smi is not found, you need to change to the proper directory in the Command Prompt window before you run the command. Use the Windows search bar to locate nvidia-smi.

Under GPU Memory Usage, you can determine whether GPU memory is being used.

To monitor the continuous usage of your GPU when running the tools, you can run nvidia-smi -l 10. You can use this to determine what the batch size should be when running the deep learning tools. If you notice there is memory not being used, you can increase the batch size. If you notice that the memory usage is at its maximum and the tool fails, decreasing the batch size should help.

Why is my CUDA GPU not working with my ArcGIS deep learning tools?

The following are possible causes:

• An out-of-date GPU driver will cause deep learning tools to fail with runtime errors, indicating that CUDA is not installed or an unsupported tool chain is present. Verify that you have the most recent GPU drivers from NVIDIA.
• Some GPUs require an NVIDIA CUDA Toolkit, which is not supported by ArcGIS. You can find the CUDA Toolkit version for each release of ArcGIS at the Manifest of included packages section of the Deep Learning Libraries Installers for ArcGIS GitHub page.

How can I speed up the inferencing tools?

If you are not already using the GPU, set Processor Type to GPU in the Environment settings of the tool. You can also increase the batch size for optimal GPU use. If the batch size is too high, the CUDA_OUT_MEMORY error may occur, and you'll need to experiment with the batch size to find the right size for your mode.

Why am I seeing conda or jupyter notebook not recognized as internal or external command when trying to install the libraries manually?

You may see these errors if you are using the standard Windows command prompt instead of ArcGIS AllSource Python Command Prompt. You can access ArcGIS AllSource Python Command Prompt from the Start menu by searching for Python Command Prompt, or you can find it in the ArcGIS AllSource installation location. ArcGIS AllSource Python Command Prompt allows you to access the standard tools and libraries that come with Conda or Jupyter.

What do I do if I see a Conda broken package error, or a verification error when trying to install libraries manually?

Clean your local cache using conda clean –t.

After training, how do I know how well my model has performed?

The output folder for the trained model contains the model_metrics.html file. This file contains information about the trained model such as the learning rate, training and validation loss, and the average precision score.

After running inferencing tools, how do I know how well my model performed?

There are various methods for verifying the results of deep learning models. For more information, see Review results.

What library versions are required for ArcGIS Pro 3.3?

For the most recent list of required libraries, see the Deep Learning Libraries Installers for ArcGIS GitHub page. The required library versions for previous versions of ArcGIS AllSource are listed in the manual installation guides (PDFs) for each version.