Machine Learning Environment Configuration

Before using the machine learning functions, you need to configure the Python environment in advance. Meanwhile, the machine learning functions have certain requirements for the software and hardware environment of the computer. For the environment configuration on Linux systems, please refer to the Machine Learning Environment Configuration_Linux page.

Recommended Basic Hardware Configuration

  • NVIDIA graphics card;
  • Video memory ≥ 10G, with a minimum requirement of 6G. Object extraction and AI-assisted editing require no less than 8G;
  • The latest graphics card driver (if it cannot be updated automatically, you can download it from the NVIDIA official website at: https://www.nvidia.cn/Download/index.aspx?lang=cn

Configure Resource Environment

Download the Windows version of the AI extension package from: https://pan.baidu.com/s/10Ec2T7HcHG0UAXR2D59UAw, extraction code: rdpd.

Note:

The AI extension package after V12.0.1 no longer supports the PaddleSegmodel algorithm for the sample library AI Label. If needed, please download the V12.0.0 or V12.0.1 version of the extension package for use. The download addresses are:

After downloading, extract it to the root directory of the SuperMap iDesktopX product package.

The SuperMap iDesktopX AI extension package provides materials such as the Python environment for AI analysis, machine learning resources, and video effects resources. The details are as follows:

  • resources_ml: Machine learning resource package, which contains resources such as sample data and model configuration files for machine learning functions;
  • support:
    • MiniConda: GPU runtime environment for AI analysis;
  • templates: Video effects resources;

Configure Python Environment

  1. Open SuperMap iDesktopX, click the Start -> Browse -> Python button. In the toolbar on the left side of the Python window, click the Python Environment Management button.
  2. In the Python Environment Management dialog box, select the SuperMap iDesktopX product package/support/MiniConda/conda/python.exe environment, click the OK button, and restart the Python environment.

Related Content

Machine Learning Environment Configuration_Linux

Imagery Analysis