Skip to content

Custom models🔗

There are instances where you may want to define your own models rather than using the pre-defined Apheris models in the model registry. In this case, you can use the custom models functionality.

If you would like to build your own custom model please contact Apheris via your personal representative or support@apheris.com who can provide the necessary credentials and more details on this process.

Examples of porting your own models can be found here:

The development path🔗

Essentially, the path to develop, activate, and run a custom model is as follows:

Model development🔗

Develop the model in your local environment. You can use the Apheris black box example in the model registry as a starting point.

Model sharing🔗

A docker image containing your model code needs to be built as the model has been developed. The built image needs to be pushed to a Quay docker repository (repository_name) that Apheris has provided you along with the associated credentials (your_quay_username and your_quay_password).

To login to the registry please use the following command and provide the password your_quay_password when prompted

docker login -u <your\_quay\_username> quay.io

To tag your image (in other words assign a version to your model) with quay_tag use the following docker command

docker tag <local\_image\_name>:<local\_tag> quay.io/apheris/<repository\_name>:<quay\_tag>

An example command to push your image to the repository repository_name

docker push quay.io/apheris/<repository\_name>:<quay\_tag>

Please register the following information while pushing the image to the repository:

  • the name of the repository repository_name where the image has been pushed
  • the tag quay_tag you assign to your image (also known as a model version)
  • the digest of your image that you can see while performing the push command (last line of the command output)
    <quay\_tag>: digest: <digest> size: <size>

Model activation🔗

Please communicate the information specified in the previous section (repository_name, quay_tag, and digest) to your Apheris representative. As soon as Apheris adds the model to the Model Registry the new version of the model will then appear on the platform and can be treated like any other model.

Running the model🔗

To run the model, a data custodian must have selected this particular model in the permissions section when setting the asset policy.