Create a Vision Model
Create a Vision Model
Create a Vision Model
Create 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 below steps to begin training your own LLM that lives locally, on your device.

Training a computer vision model

  1. Start by creating a new Canvas

  2. Drag either Object Detection or Classification Trainer Element onto the Canvas

  3. Go to settings of the Training Element. For the training data path, select the location of the training data that will be used. NOTE: For object detection training, all images must be in the same folder and formatted in the COCO JSON format.

  4. Select the output artifact path of where you would like the training artifacts to be saved.

  5. All other settings can be left as the default.

  6. Click the Run button on the Canvas. Note: The first time this flow runs, it may take a moment due to downloading

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

Using a trained computer vision model

  1. To use your newly trained inference model, create a new canvas.

  2. Then drag the inference element of the type of computer vision model you trained. This will be either an Object Detection Inference Element or a Classifier Inference Element.

  3. Once on the canvas, open the inference element's settings and select either your trained artifact from the dropdown OR file selector, not both.

  4. Now you will want to build a flow by dragging an input element onto the canvas, either Camera Element or Media Loader Element, and connecting it to the input side of your inference element. Then drag an output element, Output Preview, onto the canvas and connect it to the output side of your inference element.

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