💭 Correct way to chain frame processors?

[jslok]

Question

I have the output from rn-fast-tflite. What is the correct way to send the data to the next (custom) frame processor? If I do the below, it causes a 4+ second delay even without any code in the filterDetections plugin. If I try to send 'output' from tflite directly I get an unsupported type error.

What I tried

export function filterDetections(frame: Frame, data) {
  'worklet'
  if (plugin == null) {
    throw new Error('Failed to load Frame Processor Plugin!')
  }
  return plugin.call(frame, data)
}

  const frameProcessor = useFrameProcessor(
    (frame) => {
      'worklet'
      if (model.state !== 'loaded') {
        return
      }
        const resized = resize(frame, {
          scale: {
            width: inputSize,
            height: inputSize,
          },
          pixelFormat: 'rgb',
          dataType: dataType,
        })
        const output = model.model.runSync([resized])

        const filteredDetections = filterDetections(frame, { boxes: output[1], masks: output[2] })
    },
    [model]
  )

VisionCamera Version

beta 6

Additional information

• [X] I am using Expo
• [X] I have read the Troubleshooting Guide
• [X] I agree to follow this project's Code of Conduct
• [X] I searched for similar questions in the issues page as well as in the discussions page and found none.

[mrousavy]

You could parallelize it using runAsync