88 lines
3.1 KiB
Plaintext
88 lines
3.1 KiB
Plaintext
|
# MediaPipe graph to detect/predict face landmarks on GPU.
|
||
|
|
|
||
|
|
type: "FaceLandmarkFrontGpuImage"
|
||
|
|
|
||
|
|
# Input image. (Image)
|
||
|
|
input_stream: "IMAGE:image"
|
||
|
|
|
||
|
|
# Max number of faces to detect/track. (int)
|
||
|
|
input_side_packet: "NUM_FACES:num_faces"
|
||
|
|
|
||
|
|
# Whether landmarks on the previous image should be used to help localize
|
||
|
|
# landmarks on the current image. (bool)
|
||
|
|
input_side_packet: "USE_PREV_LANDMARKS:use_prev_landmarks"
|
||
|
|
|
||
|
|
# Whether to run face mesh model with attention on lips and eyes. (bool)
|
||
|
|
# Attention provides more accuracy on lips and eye regions as well as iris
|
||
|
|
# landmarks.
|
||
|
|
input_side_packet: "WITH_ATTENTION:with_attention"
|
||
|
|
|
||
|
|
# The throttled input image. (Image)
|
||
|
|
output_stream: "IMAGE:throttled_image"
|
||
|
|
# Collection of detected/predicted faces, each represented as a list of 468 face
|
||
|
|
# landmarks. (std::vector<NormalizedLandmarkList>)
|
||
|
|
# NOTE: there will not be an output packet in the LANDMARKS 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: "LANDMARKS:multi_face_landmarks"
|
||
|
|
|
||
|
|
# Extra outputs (for debugging, for instance).
|
||
|
|
# Detected faces. (std::vector<Detection>)
|
||
|
|
output_stream: "DETECTIONS:face_detections"
|
||
|
|
# Regions of interest calculated based on landmarks.
|
||
|
|
# (std::vector<NormalizedRect>)
|
||
|
|
output_stream: "ROIS_FROM_LANDMARKS:face_rects_from_landmarks"
|
||
|
|
# Regions of interest calculated based on face detections.
|
||
|
|
# (std::vector<NormalizedRect>)
|
||
|
|
output_stream: "ROIS_FROM_DETECTIONS:face_rects_from_detections"
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "FlowLimiterCalculator"
|
||
|
|
input_stream: "image"
|
||
|
|
input_stream: "FINISHED:multi_face_landmarks"
|
||
|
|
input_stream_info: {
|
||
|
|
tag_index: "FINISHED"
|
||
|
|
back_edge: true
|
||
|
|
}
|
||
|
|
output_stream: "throttled_image"
|
||
|
|
options: {
|
||
|
|
[mediapipe.FlowLimiterCalculatorOptions.ext] {
|
||
|
|
max_in_flight: 1
|
||
|
|
max_in_queue: 1
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
# Converts Image to GpuBuffer for FaceLandmarkFrontGpu to consume.
|
||
|
|
node {
|
||
|
|
calculator: "FromImageCalculator"
|
||
|
|
input_stream: "IMAGE:throttled_image"
|
||
|
|
output_stream: "IMAGE_GPU:raw_gpu_buffer"
|
||
|
|
output_stream: "SOURCE_ON_GPU:is_gpu_image"
|
||
|
|
}
|
||
|
|
|
||
|
|
# TODO: Remove the extra flipping once adopting MlImage.
|
||
|
|
# If the source images are on gpu, flip the data vertically before sending them
|
||
|
|
# into FaceLandmarkFrontGpu. This maybe needed because OpenGL represents images
|
||
|
|
# assuming the image origin is at the bottom-left corner, whereas MediaPipe in
|
||
|
|
# general assumes the image origin is at the top-left corner.
|
||
|
|
node: {
|
||
|
|
calculator: "ImageTransformationCalculator"
|
||
|
|
input_stream: "IMAGE_GPU:raw_gpu_buffer"
|
||
|
|
input_stream: "FLIP_VERTICALLY:is_gpu_image"
|
||
|
|
output_stream: "IMAGE_GPU:gpu_buffer"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "FaceLandmarkFrontGpu"
|
||
|
|
input_stream: "IMAGE:gpu_buffer"
|
||
|
|
input_side_packet: "NUM_FACES:num_faces"
|
||
|
|
input_side_packet: "USE_PREV_LANDMARKS:use_prev_landmarks"
|
||
|
|
input_side_packet: "WITH_ATTENTION:with_attention"
|
||
|
|
output_stream: "LANDMARKS:multi_face_landmarks"
|
||
|
|
output_stream: "DETECTIONS:face_detections"
|
||
|
|
output_stream: "ROIS_FROM_LANDMARKS:face_rects_from_landmarks"
|
||
|
|
output_stream: "ROIS_FROM_DETECTIONS:face_rects_from_detections"
|
||
|
|
}
|