Import Model

External models can be imported into the Data Science Lab and experimented inside the Notebooks using the Import Model functionality.

Please Note:

• The External models can be registered to the Data Pipeline module and inferred using the Data Science Lab script runner.

• Only the Native prediction functionality will work for the External models.

Importing a Model

Check out the illustration on importing a model.

Importing a Model

• Navigate to the Model tab for a Data Science Project.

• Click the Import Model option.

• The user gets redirected to upload the model file. Select and upload the file.

• A notification message appears.

• The imported model gets added to the model list.

Please Note: The imported models are referred to as External models in the model list and are marked with a prefix to their names (as displayed in the above-given image).

Exporting a Model to the Data Pipeline

You can integrate and export cutting-edge Data Science models into your data pipeline, ensuring optimized performance, real-time insights, and data-driven decision-making. The user needs to start a new .ipynb file with a wrapper function that includes Data, Imported Model, Predict function, and output Dataset with predictions.

• Navigate to a Data Science Notebook (.ipynb file) from an activated project. In this case, a notebook has been imported with the wrapper function.

• Access the Imported Model inside this .ipynb file.

• Load the imported model to the Notebook cell.

• Mention the loaded model in the inference script.

• Run the code cell with the inference script.

• The Data preview is displayed below.

• Click the Register option for the imported model from the ellipsis context menu.

• The Register Model dialog box appears to confirm the model registration.

• Click the Yes option.

• A notification message appears, and the model gets registered.

• Export the script using the Export functionality provided for the Data Science Notebook (.ipynb file).

• Another notification appears to ensure that the Notebook is saved.

• The Export to Pipeline window appears.

• Select a specific script from the Notebook. or Choose the Select All option to select the full script.

• Select the Next option.

• Click the Validate icon to validate the script.

• A notification message appears to ensure the validity of the script.

• Click the Export to Pipeline option.

• A notification message appears to ensure that the selected Notebook has been exported.

Please Note: The imported model gets registered to the Data Pipeline module as a script.

Accessing the Exported Model within the Pipeline User interface

• Navigate to the Data Pipeline Workflow editor.

• Drag the DS Lab Runner component and configure the Basic Information.

• Open the Meta Information tab of the DS Lab Runner component.

• Configure the following information for the Meta Information tab.

  • Select Script Runner as the Execution Type.

  • Select function input type.

  • Select the project name.

  • Select the Script Name from the drop-down option. The same name given to the imported model appears as the script name.

  • Provide details for the External Library (if applicable).

  • Select the Start Function from the drop-down menu.

• The exported model can be accessed inside the Script section.

• The user can connect the DS Lab Script Runner component to an Input Event.

• Run the Pipeline.

• The model predictions can be generated in the Preview tab of the connected Input Event.

Please Note:

• The Imported Models can be accessed through the Script Runner component inside the Data Pipeline module.

• The execution type should be Model Runner inside the Data Pipeline while accessing the other exported Data Science models.

• The supported extensions for External models - .pkl, .h5, .pth & .pt

Try out the Import Model Functionality yourself

Some of the Sample models and related scripts are provided below for the users to try this functionality. Please download them with a click, and use them inside your Data Science Notebook by following the above-mentioned steps.

Sample files for Sklearn

923B

SklearnModel .pkl

Open

Sample Sklearn model for import.

6KB

Importmodels_Sklearn_Inference (1).ipynb

Open

Sample python script based on the imported Sklearn model.

Sample files for Keras

18KB

KersModel.h5

Open

Sample Keras model for import.

6KB

Importmodels_Keras_Inference.ipynb

Open

Sample python script based on the imported Keras model.

Sample files for PyTorch

8KB

Pytorch_Model.pth

Open

Sample Pytorch model for import

10KB

ImportModel_Pytorch_Inference.ipynb

Open

Sample python script based on the imported Pytorch model.