Quality Control

If you want to use a camera that is not your webcam, you can add a custom camera to your setup.

If you prefer to analyze pictures or a video, you can use Media Loader instead of Camera for your image input.

Setting Up

1. using the ... button in the top right corner, open the settings on the Image Classification Inference element.
   1. Select a trained model from the drop-down or, upload one via Select Directory button.
   2. Select a Minimum confidence threshold for bounding boxes.
2. If you want to simply see the inference from the model, you can delete the Image Inference Saver, and hit the Run button up top.

If you want to save the images from the feed with bounding boxes and annotations for further analysis or training:

1. Open the settings for the Image Inference Saver.
2. Select the folder you want the images and annotations saved to in the 'Output Folder Path.'
3. Name the Partition inside the folder.
4. Select the format you want the images saved as (jpg, pmg, or npy).
5. Select if you want to save:
   • Images
   • Annotations
   • Bounding Boxes on the images
6. Set minimum confidence threshold to save.
7. You can now hit Run and Open the Output Preview when the link appears.

Dependencies will be installed the first time this flow is run and may take a while.