# MediaPipe graph that performs face detection with TensorFlow Lite on CPU.

input_stream: "VIDEO:input_video"
output_stream: "DETECTIONS:output_detections"


# Transforms the input image on CPU to a 128x128 image. To scale the input
# image, the scale_mode option is set to FIT to preserve the aspect ratio,
# resulting in potential letterboxing in the transformed image.
node: {
  calculator: "ImageTransformationCalculator"
  input_stream: "IMAGE:input_video"
  output_stream: "IMAGE:transformed_input_video_cpu"
  output_stream: "LETTERBOX_PADDING:letterbox_padding"
  options: {
    [mediapipe.ImageTransformationCalculatorOptions.ext] {
      output_width: 192
      output_height: 192
      scale_mode: FIT
    }
  }
}

# Converts the transformed input image on CPU into an image tensor stored as a
# TfLiteTensor.
node {
  calculator: "TfLiteConverterCalculator"
  input_stream: "IMAGE:transformed_input_video_cpu"
  output_stream: "TENSORS:image_tensor"
}

# Runs a TensorFlow Lite model on CPU that takes an image tensor and outputs a
# vector of tensors representing, for instance, detection boxes/keypoints and
# scores.
node {
  calculator: "TfLiteInferenceCalculator"
  input_stream: "TENSORS:image_tensor"
  output_stream: "TENSORS:detection_tensors"
  options: {
    [mediapipe.TfLiteInferenceCalculatorOptions.ext] {
      model_path: "mediapipe/modules/face_detection/face_detection_back.tflite"
    }
  }
}

# Generates a single side packet containing a vector of SSD anchors based on
# the specification in the options.
node {
  calculator: "SsdAnchorsCalculator"
  output_side_packet: "anchors"
  options: {
    [mediapipe.SsdAnchorsCalculatorOptions.ext] {
      num_layers: 1
      min_scale: 0.1484375
      max_scale: 0.75
      input_size_height: 192
      input_size_width: 192
      anchor_offset_x: 0.5
      anchor_offset_y: 0.5
      strides: 4
      aspect_ratios: 1.0
      fixed_anchor_size: true
      interpolated_scale_aspect_ratio: 0.0
    }
  }
}

# Decodes the detection tensors generated by the TensorFlow Lite model, based on
# the SSD anchors and the specification in the options, into a vector of
# detections. Each detection describes a detected object.
node {
  calculator: "TfLiteTensorsToDetectionsCalculator"
  input_stream: "TENSORS:detection_tensors"
  input_side_packet: "ANCHORS:anchors"
  output_stream: "DETECTIONS:detections"
  options: {
    [mediapipe.TfLiteTensorsToDetectionsCalculatorOptions.ext] {
      num_classes: 1
      num_boxes: 2304
      num_coords: 16
      box_coord_offset: 0
      keypoint_coord_offset: 4
      num_keypoints: 6
      num_values_per_keypoint: 2
      sigmoid_score: true
      score_clipping_thresh: 100.0
      reverse_output_order: true
      x_scale: 192.0
      y_scale: 192.0
      h_scale: 192.0
      w_scale: 192.0
      min_score_thresh: 0.6
    }
  }
}

# Performs non-max suppression to remove excessive detections.
node {
  calculator: "NonMaxSuppressionCalculator"
  input_stream: "detections"
  output_stream: "filtered_detections"
  options: {
    [mediapipe.NonMaxSuppressionCalculatorOptions.ext] {
      min_suppression_threshold: 0.3
      overlap_type: INTERSECTION_OVER_UNION
      algorithm: WEIGHTED
      return_empty_detections: true
    }
  }
}

# Adjusts detection locations (already normalized to [0.f, 1.f]) on the
# letterboxed image (after image transformation with the FIT scale mode) to the
# corresponding locations on the same image with the letterbox removed (the
# input image to the graph before image transformation).
node {
  calculator: "DetectionLetterboxRemovalCalculator"
  input_stream: "DETECTIONS:filtered_detections"
  input_stream: "LETTERBOX_PADDING:letterbox_padding"
  output_stream: "DETECTIONS:output_detections"
}