Core Concepts

For a full example how to build your own pipeline and NOT using the predefined .denkflow files see here

Pipeline, Nodes, and Tensors

• Pipeline - The main object representing a data processing graph. You can load a pre-built graph or construct one manually.
• Node - A processing unit within the pipeline (e.g., image resizing, object detection, OCR). Nodes have input and output topics.
• Tensor - The data format exchanged between nodes (e.g., ImageTensor, BoundingBoxTensor, OcrTensor).

Model Formats: .denkflow vs .denkmodel

Denkflow uses two primary model file types obtained from the DENKweit Vision AI Hub:

1. .denkflow files (Complete Pipelines):

   • These represent entire, pre-configured processing graphs.
   • They are exported from the "Exports" tab of your model on the Vision AI Hub.
   • Loaded using Pipeline.from_denkflow(...).
   • This is currently the only method for using quantized models exported from the Hub.

2. .denkmodel files (Individual AI Models):

   • These contain single AI models (e.g., for object detection, classification, OCR) without the surrounding pipeline structure.
   • They are downloaded directly from the "Network Details" page of your model on the Vision AI Hub.
   • Used when building custom pipelines by adding specific AI nodes (e.g., pipeline.add_object_detection_node(...)).
   • Currently, .denkmodel files downloaded this way are not quantized. Support for downloading single quantized models will be added later.