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

SSD_TO_BBOX

SSDToBoundingBoxStep is a pipeline step that configures extraction of bounding boxes from a (Single-Shot Detector) SSD model output.

Configs

Descriptions

classLabels

A list of class labels

keepOtherValues

true by default. If true, other data key and values from the previous step are kept and passed on to the next step as well.

threshold

Threadshold to the output of the SSD models for fetching bounding boxes for. Default threshold is 0.5.

scale

An optional way to increase the size of the bounding boxes by some fraction. If specified, a value of 1.0 is equivalent to no scaling. A scale of 2.0 means the center is unchanged, but the width and height are now two times larger than it would be.

aspectRatio

An optional way to control the output shape (aspect ratio) of the bounding boxes. Defined in terms of width or height. If specified, an aspect ratio of 1.0 gives a square output; an aspect ratio of 2.0 gives twice as wide as it is high. Note that for making the output the correct aspect ratio, one of the height or width will be increased; the other dimension will not change. The pre-aspect-ratio-corrected box will be contained fully within the output box.

outputName

Output key name where the bounding box will be contained in. The default name is bounding_box.

PreviousEXTRACT_BOUNDING_BOXNextYOLO_BBOX

Last updated 4 years ago

Was this helpful?