LogoLogo
HomeCommunity
EN master
EN master
  • Introduction
  • Components
  • Quickstart
    • Using Docker
    • Using Java SDK
    • Using Python SDK
    • Using CLI
  • Building from source
  • Installing Binaries
  • Configurations
    • JSON
    • YAML
  • GitHub
  • Examples
    • Java
      • Server
        • Pipeline Steps
          • Image To NDArray Step
          • Python Step
          • DL4J Step
          • Keras Step
          • ONNX Step
          • Tensorflow Step
        • Sequence Pipeline
        • Graph Pipeline
      • Client
        • Running Predictions
        • Inspecting a Server
    • Python
      • Server
        • Pipeline Steps
          • Image To NDArray Step
          • Python Step
          • DL4J Step
        • Sequence Pipeline
        • Graph Pipeline
      • Client
        • Running Predictions
        • Inspecting a Server
    • IPython Notebook
      • Basic
      • ONNX
        • Pytorch (IRIS)
        • Pytorch (MNIST)
      • Keras
      • Tensorflow
      • DL4J
    • CLI
      • Use-Cases
        • Creating a Sequence Pipeline
        • Creating a Graph Pipeline
        • Create Server URL with Inspection Queries
        • Adding Extra Classpaths
        • Multiple Instances of a Server
      • Commands
        • Serve Command
        • Logs Command
        • Inspect Command
        • Profile Command
  • How-To Guides
    • Serving a BMI Model
      • With HTML Content
    • Performing Object Detection
    • RPA Use-Case
    • Showing Metrics
      • Prometheus
      • Grafana
  • References
    • Pipeline Steps
      • IMAGE_TO_NDARRAY
      • IMAGE_CROP
      • IMAGE_RESIZE
      • DEEPLEARNINGL4J
      • KERAS
      • ND4JTENSORFLOW
      • ONNX
      • TENSORFLOW
      • SAMEDIFF
      • CLASSIFIER_OUTPUT
      • REGRESSION_OUTPUT
      • LOGGING
      • BOUNDING_BOX_FILTER
      • BOUNDING_BOX_TO_POINT
      • CROP_GRID
      • CROP_FIXED_GRID
      • DRAW_BOUNDING_BOX
      • DRAW_FACE_KEY_POINT
      • DRAW_GRID
      • DRAW_FIXED_GRID
      • DRAW_HEATMAP
      • DRAW_POINTS
      • DRAW_SEGMENTATION
      • EXTRACT_BOUNDING_BOX
      • SSD_TO_BBOX
      • YOLO_BBOX
      • RELATIVE_TO_ABSOLUTE
      • SHOW_IMAGE
      • FRAME_CAPTURE
      • VIDEO_CAPTURE
      • PERSPECTIVE_TRANSFORM
    • Inference Configuration
      • MQTT Configuration
      • KAFKA Configuration
    • CLI Commands
      • Serve Command
      • Logs Command
      • Inspect Command
      • Pythonpaths Command
      • Build Command
      • Config Command
      • Predict Command
      • Profile Command
  • Change Logs
    • Version 0.1.0
  • Contribution Guidelines
Powered by GitBook
On this page

Was this helpful?

  1. References
  2. Pipeline Steps

RELATIVE_TO_ABSOLUTE

PreviousYOLO_BBOXNextSHOW_IMAGE

Last updated 4 years ago

Was this helpful?

RelativeToAbsoluteStep is used for a given set of points, list of point, bounding box} or list of bounding boxes that are defined in relative terms. For example, all values 0.0 to 1.0 in terms of fraction of image height/width, convert these to absolute values (i.e., pixels) using:

  1. An input image, as specified via the image name configuration, OR

  2. An image height, as specified by image height and image width configuration.

Note that an ImageToNDArrayConfig can be provided, to account for the fact that the original image may have been cropped before being passed into a network that produced the points or bounding boxes. If the imageToNDArrayConfig field is null, it is assumed no cropping has occurred.

Configs

Descriptions

imageName

Optional - the name of the field in the input data containing the image to use (to determine height/width).

imageH

If imageName is not specified - height of the input image to use.

imageW

If imageName is not specified - width of the input image to use.

imageToNDArrayConfig

Optional - used to account for the fact that the image may have been cropped before being passed into a network that produced the points or bounding box. This allows for them to be offset, so the boxes or coordinates are specified in terms of the original image, not the cropped image. Refer config from .

toConvert

Optional - the name of the point, list of point, bounding box or list of bounding box fields to convert. If not set, the step will convert any/all fields of those types.

IMAGE_TO_NDARRAY