Skip to main content
Version: 2024.1

Hugging Face Zero Shot Image Classification

This action can be executed on an image level lets you automatically send selected images to a configurable Hugging Face endpoint to classify the images according to the configured Tags in pimcore. For more information about the Hugging Face Zero Shot Image Classification, please visit Hugging Face Zero Shot Image Classification.

Configuration Options​

tag_root_node: 1
tag_only_leaf_nodes: true
replace_existing_tags: true
minimum_confidence: 0.8
best_match_only: false
model_endpoint: 'https://api-inference.huggingface.co/models/openai/clip-vit-large-patch14-336'

Detailed Configuration Options​

  • tag_root_node: Type: Integer. Default: 0. The Root Tag to be used for the classification
  • tag_only_leaf_nodes: Type: Boolean. Default: false. If true, only leaf nodes of the tag tree will be used for the classification
  • replace_existing_tags: Type: Boolean. Default: false. If true, existing tags will be replaced with the new ones
  • minimum_confidence: Type: Float. Default: 0.8. The minimum confidence for a tag to be added to the image.
  • best_match_only: Type: Boolean. Default: true. If true, only the best match will be used otherwise the minimum confidence will be used and all tags with a confidence higher than the minimum confidence will be used
  • model_endpoint: Type: String. Endpoint url of the Hugging Face model to use.
  • tag_limit: Type: Integer. Default: 10. The maximum number of tags that can be passed to the classification model. Currently, the Hugging Face model only supports up to 10 tags.