Image aesthetic scoring

Prerequisites

• You can use the workflow feature only after you purchase the unstructured data feature for the instance.

• A workflow is created. For more information, see Create a workflow.

Background information

• The Image Aesthetic Scoring operator can process files in the following formats: JPG, JPEG, JPE, JFIF, PNG, BMP, TIFF, TIF, WebP, HEIC, HEIF, GIF, ICO, PPM, PGM, PBM, PNM, TGA, and SVG.

• When the Image Aesthetic Scoring operator uses a System-built-in model, it is allocated 1 core and 4 GB of resources by default. When it uses a Multi-modal LLM, it is allocated 0.5 cores and 1 GB of resources by default.

Permissions

In a Basic project, project administrators, developers, analysts, and custom project roles with the Dataset-Use permission can use all datasets within the project for the operator's input and output.

Procedure

1. From the top menu bar on the Dataphin home page, choose R&D > Data R&D.

2. From the top menu bar on the Developer page, select a Project.

3. In the navigation pane on the left, choose Data Processing > Workflow. In the Workflow list on the left, click the desired workflow to open its canvas. From the Operator Library on the left, drag the Image Aesthetic Scoring operator to the canvas. In the Image Aesthetic Scoring panel on the right, configure the parameters.

   Parameter		Description
   Step Name		Enter a name for the operator. The name can contain any characters and be up to 256 characters in length.
   Input Configuration	Dataset	Select the dataset to process. You can select only Hybrid datasets. After you select a dataset, select a Version. The default is the first version of the dataset. If this operator is a downstream component of another operator, the selected dataset is typically the same as the output dataset of the upstream operator.
   	Input Field	The storage URL of the image to process. Select a source field from the input dataset. You can select only fields for which the Is URL parameter is set to Yes.
   	Filter Condition (optional)	Use SQL syntax. Enter only the filter condition that follows the WHERE clause. You can use system global variables, such as the data timestamp ${bizdate}.
   Operator Configuration	Processing Model	Select a System-built-in model (CLIP) or a Multi-modal LLM. If you select a multi-modal LLM, you must specify the Model for the operator. You can select only models that are enabled and have a model type that includes Vision (Images and Videos) in Intelligent Application Management > Model Configuration.
   Output Configuration	Dataset	You can select the Source dataset or Another dataset. If the metadata table of the source dataset does not have a primary key, Another dataset is selected by default. If you select Another dataset, you must also specify a Hybrid dataset or a Table dataset and its Version as the output dataset. The default is the first version of the dataset. You can also select other versions of the source dataset. If you select the source dataset, the metadata generated by the operator is written to the metadata table that corresponds to the same version of the source dataset.
   	Loading Policy	If the metadata table of the selected output dataset has a primary key, Update on primary key conflict is selected by default. If no primary key exists, Append data is selected by default. Append data: Appends data directly to the destination table. A fault is reported in the case of a primary key or constraint violation. Update on primary key conflict: In the case of a primary key or constraint violation, the entire row of old data with the duplicate primary key is deleted before the new data is inserted. Overwrite: Deletes the data in the destination table before writing the new data. Note If you set Dataset to Source dataset, the only supported loading policy is Update on primary key conflict.
   	Field Mapping	The Image Aesthetic Scoring operator has the following fixed output field: aesthetic_score: The score ranges from 0 to 1. A higher score indicates better aesthetic quality. A score greater than 0.5 is generally considered good. By default, the operator's output fields are mapped to fields with the same names in the output dataset. You can also manually select destination fields for custom mapping. In addition, you can map pass-through fields from the source dataset to the destination dataset. You can manage field mappings in the following ways: Add Output Field: Click to add a blank field mapping row. This feature is available only when you set the output dataset to Another dataset. Batch Mapping: Click to perform batch manual mapping, same-name mapping, or same-row mapping. This feature is available only when you set the output dataset to Another dataset. Delete Mapping: Click the Delete icon to delete the corresponding field mapping row. You cannot delete the mapping for the operator's fixed output field.

4. After you complete the configuration, click Save in the menu bar at the top of the canvas.

   After you configure an operator, you can continue to select its upstream or downstream operators to complete the full workflow configuration.