# MediaPipe graph to detect faces.
#
# EXAMPLE:
# node {
# calculator: "FaceDetectionFrontCpu"
# input_stream: "IMAGE:image"
# input_stream: "ROI:roi"
# output_stream: "DETECTIONS:face_detections"
# }
type: "FaceDetection"
# The input image, either ImageFrame, GpuBuffer, or (multi-backend) Image.
input_stream: "IMAGE:image"
# ROI (region of interest) within the given image where faces should be
# detected. (NormalizedRect)
input_stream: "ROI:roi"
# Detected faces. (std::vector<Detection>)
# NOTE: there will not be an output packet in the DETECTIONS stream for this
# particular timestamp if none of faces detected. However, the MediaPipe
# framework will internally inform the downstream calculators of the absence of
# this packet so that they don't wait for it unnecessarily.
output_stream: "DETECTIONS:detections"
graph_options: {
[type.googleapis.com/mediapipe.FaceDetectionOptions] {}
}
# Converts the input CPU or GPU image to the multi-backend image type (Image).
node: {
calculator: "ToImageCalculator"
input_stream: "IMAGE:image"
output_stream: "IMAGE:multi_backend_image"
}
# Transforms the input image into a 128x128 tensor while keeping the aspect
# ratio (what is expected by the corresponding face detection model), resulting
# in potential letterboxing in the transformed image.
node: {
calculator: "ImageToTensorCalculator"
input_stream: "IMAGE:multi_backend_image"
input_stream: "NORM_RECT:roi"
output_stream: "TENSORS:input_tensors"
output_stream: "MATRIX:transform_matrix"
options: {
[mediapipe.ImageToTensorCalculatorOptions.ext] {
keep_aspect_ratio: true
output_tensor_float_range {
min: -1.0
max: 1.0
}
border_mode: BORDER_ZERO
}
}
option_value: "gpu_origin:options/gpu_origin"
option_value: "output_tensor_width:options/tensor_width"
option_value: "output_tensor_height:options/tensor_height"
}
# 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: "InferenceCalculator"
input_stream: "TENSORS:input_tensors"
output_stream: "TENSORS:detection_tensors"
options: {
[mediapipe.InferenceCalculatorOptions.ext] {}
}
option_value: "delegate:options/delegate"
option_value: "model_path:options/model_path"
}
# Detection tensors. (std::vector<Tensor>)
#input_stream: "TENSORS:detection_tensors"
# A 4x4 row-major-order matrix that maps a point represented in the detection
# tensors to a desired coordinate system, e.g., in the original input image
# before scaling/cropping. (std::array<float, 16>)
#input_stream: "MATRIX:transform_matrix"
# Detected faces. (std::vector<Detection>)
# NOTE: there will not be an output packet in the DETECTIONS stream for this
# particular timestamp if none of faces detected. However, the MediaPipe
# framework will internally inform the downstream calculators of the absence of
# this packet so that they don't wait for it unnecessarily.
#output_stream: "DETECTIONS:detections"
# 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
anchor_offset_x: 0.5
anchor_offset_y: 0.5
aspect_ratios: 1.0
fixed_anchor_size: true
}
}
option_value: "input_size_width:tensor_width"
option_value: "input_size_height:tensor_height"
option_value: "num_layers:num_layers"
option_value: "strides:strides"
option_value: "interpolated_scale_aspect_ratio:interpolated_scale_aspect_ratio"
}
# 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: "TensorsToDetectionsCalculator"
input_stream: "TENSORS:detection_tensors"
input_side_packet: "ANCHORS:anchors"
output_stream: "DETECTIONS:unfiltered_detections"
options: {
[mediapipe.TensorsToDetectionsCalculatorOptions.ext] {
num_classes: 1
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
}
}
option_value: "num_boxes:num_boxes"
option_value: "x_scale:x_scale"
option_value: "y_scale:y_scale"
option_value: "h_scale:h_scale"
option_value: "w_scale:w_scale"
option_value: "min_score_thresh:min_score_thresh"
}
# Performs non-max suppression to remove excessive detections.
node {
calculator: "NonMaxSuppressionCalculator"
input_stream: "unfiltered_detections"
output_stream: "filtered_detections"
options: {
[mediapipe.NonMaxSuppressionCalculatorOptions.ext] {
min_suppression_threshold: 0.3
overlap_type: INTERSECTION_OVER_UNION
algorithm: WEIGHTED
}
}
}
# Projects the detections from input tensor to the corresponding locations on
# the original image (input to the graph).
node {
calculator: "DetectionProjectionCalculator"
input_stream: "DETECTIONS:filtered_detections"
input_stream: "PROJECTION_MATRIX:transform_matrix"
output_stream: "DETECTIONS:detections"
}