📄️ Basic classification
This example loads a complete classification pipeline file (.denkflow) exported from the Hub.
📄️ Basic object detection
This example loads a complete object detection pipeline file (*.denkflow) exported from the Hub.
📄️ PipelineWrapper
This example runs an exported object-detection .denkflow through PipelineWrapper and draws annotated images. Results are returned in absolute pixel coordinates, ready to use without subscribe/receive or tensor decoding.
📄️ Basic segmentation
This example loads a complete segmentation pipeline file (.denkflow) exported from the Hub.
📄️ Basic instance segmentation
This example loads a complete instance segmentation pipeline file (.denkflow) exported from the Hub. An instance segmentation network returns bounding box tensors and segmentation tensors, which need to be combined in the to_objects-function.
📄️ Evaluating a sequence of images
This is a modification of the classification example to highlight how to evaluate a sequence of images.
📄️ Optical character recognition (OCR)
This example shows how to load a pre-built OCR pipeline from a .denkflow file.
📄️ Configuration options
<Tabs
📄️ Ready-to-use OCR package
This is a ready-to-use example. All authentication, models, images and example Dockerfile are included. Download it here:
📄️ Custom pipeline construction
This example shows how to build a pipeline manually, adding an object detection node that uses an .denkmodel model file.
📄️ Runtime parameters on exported pipelines
Exported .denkflow files from the Vision AI Hub can embed constant topic values — for example bounding-box filter thresholds (/iouthreshold, /scorethreshold) or resize dimensions (/image_size).