Procedure

• If this is your first login to MindStudio, click New Project on the MindStudio welcome window to go to the project creation page.
• If this is not your first login to MindStudio, choose File > New > Project... form the menu bar to go to the project creation page.
  Figure 1 Create Ascend Training Project
  

  

  During first-time sample project creation, ensure that the development environment is connected to the Internet. You can download the sample project template and decompress it to MindStudio_installation_directory/plugins/ascend-foundation/samples/advisor/ to ensure that new sample projects can be properly created. If you do not need to create sample projects, you can decompress the downloaded sample project template to any directory and choose File > Open... in MindStudio to open it.

1. In the navigation pane on the left, select Ascend Advisor. Configure the CANN version on the right, as shown in Figure 1.
2. Click Next to set the project parameters, as described in Table 1.

   Table 1 Project parameters

   Parameter	Description
   Project name	Project name (user-defined). The name contains a maximum of 64 characters, starting with a letter and ending with a letter or digit. Only letters, digits, hyphens (-), and underscores (_) are allowed.
   Project location	Default path for saving a project (user-defined). (For users who use MindStudio for the first time, the default value is $HOME/MindstudioProjects)
   More Settings	Module name: module name, same as the Project name.
   	Content root: path in the root directory.
   	Module file location: module file path.
   	Click the check box on the right of Project format. A drop-down list is displayed. .idea (directory-based) (default option): During project creation, an .idea project directory is created to save the project information. .ipr (file-based): project configuration file used to save the project configuration information.

3. Click Finish. See Figure 2.
   Figure 2 Ecosystem repository sample project
   
4. If there is already an active project in the window, a confirmation message is displayed.
   • Click This Window to open the created project in the current window.
   • Click New Window to open the created project in a new window.

1. Modify the ecosystem.json file.
   For details about the parameters, see Table 3.

   {
       "model_list": [
           {
               "model_name": "model",
               "session_list": [
                   {
                       "python_model_path": "./model/src/"
                   }
               ]
           }
       ]
   }

   Table 3 Parameters in ecosystem.json

   Parameter	Description	Mandatory or Not
   model_name	Ecosystem repository name (that is, source code file name).	Yes
   python_model_path	Directory where the source code file is located. The relative path can be identified, so you can configure this path to the directory where the ecosystem.json file is located.	Yes

2. Before using the ecosystem repository in other environments, run the pip3 install –r requirements.txt command to install the dependency library.
3. Develop the ecosystem repository code in the model.py file.

MindStudio IDE does not support the Advisor-based performance analysis function of the ecosystem repository.