The Publish ENVI ONNX Model tool uploads a configured Deep Learning ONNX model package to an ENVI Repository.

You can also write a script to publish Deep Learning ONNX models to the ENVI Repository using the PublishENVIDeepLearningOnnxModel task.

  1. From the ENVI Toolbox, select Deep Learning > Publish ENVI ONNX Model. The Publish ENVI ONNX Model dialog appears.
  2. Click the Browse button next to the Input Model field. The Select Deep Learning ONNX Model File dialog appears.
  3. Select the model to publish. If trained models are saved to the Output Directory set in your ENVI preference, they will automatically appear in the list of models. Or, to select a trained model file from a different directory, click the Open button , select the model, and click Open to add it to the list of models.
  4. Enter a Name for the package.
  5. Enter a Display Name for the package, if you want the name that appears in the ENVI Repository to be different from the entry in Name.
  6. Optionally, enter a Description of the package.
  7. Enter a Version number for the ONNX model (example: 1.0.0). This parameter is used to track the iteration or release of the model for documentation, debugging, and compatibility purposes. This number can be incremented if the model already exists and you are publishing a new version of it.
  8. In the Repository URL drop-down list, select a registered repository to which to publish the package. Or, enter the URL and port number for an ENVI Repository server.

  9. To reuse these task settings in future ENVI sessions, save them to a file. Click the down arrow next to the OK button and select Save Parameter Values, then specify the location and filename to save to. Note that some parameter types, such as rasters, vectors, and ROIs, will not be saved with the file. To apply the saved task settings, click the down arrow and select Restore Parameter Values, then select the file where you previously stored your settings.

  10. To run the process in the background, click the down arrow and select Run Task in the Background. If an ENVI Server has been set up on the network, the Run Task on remote ENVI Server name is also available. The ENVI Server Job Console will show the progress of the job and will provide a link to display the result when processing is complete. See the ENVI Servers topic in ENVI Help for more information.

  11. Click OK to upload the package.

See Also

Configure ONNX Model, Refer to the "ENVI Repository" topic in ENVI Help for more details on the repository.