Creating a Vision Model


If you want to create a vision-based solution for your use case, then training a computer vision model is what you need. Follow the steps below to begin training your own model that lives locally, on your device.

Computer Vision Model Training

  1. Start by creating a new Canvas

  2. Add a Trainer Element

    • Open the Elements Drawer
    • Drag either the Object Detection or Classification Trainer element onto the Canvas
  3. Configure the Trainer Element

    Open the Trainer Element settings and adjust the following:

    • Training data path: Using the Select Directory button, choose the folder where your training data is located

      For object detection training, all images must be in the same folder and formatted in the COCO JSON format

    • Output artifact path: Using the Select Directory button, choose the folder where you would like to save the training artifacts

    • Other settings: Leave all other settings as the default

  4. Run the Canvas

    The first time this flow runs, it may take a moment due to downloading dependencies

Once the training is completed, you will have a selectable computer vision inference model

Computer Vision Model Inference

To use your newly trained inference model, follow these steps:

  1. Create a new Canvas

  2. Add an Inference Element

    • Drag the inference element of the type of computer vision model you trained onto the Canvas
    • This will be either an Object Detection Inference Element or a Classifier Inference Element
  3. Configure the Inference Element

    • Open the inference element's settings
    • Select either your trained artifact from the dropdown or file selector, not both
  4. Add an Input Source

    • Drag an input element onto the canvas
    • Use either a Camera Element or Media Loader Element
    • Connect it to the input side of your inference element

    If you are using a Camera Element, you must first have an input device configured under the Devices tab

  5. Add an Output Display

    • Drag an Output Preview element onto the canvas
    • Connect it to the output side of your inference element
  6. Run the Canvas to view your model results