Upload Pretrained Models: Currently, AryaXAI supports the upload of deep learning (DL) models built using TensorFlow

Deep Learning Support (for Tabular Data Projects)

Integrated deep learning model support is currently available only for the tabular modality and is compatible with TensorFlow models.

Uploading own models

1. Upload model manually

When uploading own models, users need to:

1. Navigate to the 'Model upload' tab in Data settings
2. Define the model name: Provide a name for your model.
3. Specify Model Architecture: Indicate whether the model is based on machine learning or deep learning (deep learning support is coming soon).
4. Select the compute server
5. Specify Training and Testing tags: Provide the tags to be used for training and testing the model.

NOTE: If the training and testing data are not provided, AryaXAI will automatically select a random sub-sample from the training data to use as testing data. This allows AryaXAI to benchmark your uploaded model against a subset of the training data.

NOTE: Ensure that all features used in your model are presented in the data you have uploaded ie; data points in the model and uploaded file need to be the same.

‍

Following are the models that you can upload to AryaXAI:

• XGBoost
• LGBoost
• CatBoost
• RandomForest
• SGD (Stochastic Gradient Descent)
• Logistic Regression
• Linear Regression
• GaussianNaiveBayes

NOTE: Deep Learning is not available at the moment. Only use ML.

2. Upload model via connectors

Connectors include S3, GCS, Google Drive, SFTP, and Dropbox. Access to these connectors depends on your subscription plan. You can add new connectors and view the list of existing connectors through the ‘Connectors’ option in the main menu on the left.