mediapipe-rs/mediapipe/graphs/pose_tracking/pose_tracking_cpu.pbtxt

64 lines
2.3 KiB
Plaintext
Raw Normal View History

2022-03-01 13:04:01 +01:00
# MediaPipe graph that performs pose tracking with TensorFlow Lite on CPU.
# CPU buffer. (ImageFrame)
input_stream: "input_video"
# Output image with rendered results. (ImageFrame)
output_stream: "output_video"
# Pose landmarks. (NormalizedLandmarkList)
output_stream: "pose_landmarks"
# Generates side packet to enable segmentation.
node {
calculator: "ConstantSidePacketCalculator"
output_side_packet: "PACKET:enable_segmentation"
node_options: {
[type.googleapis.com/mediapipe.ConstantSidePacketCalculatorOptions]: {
packet { bool_value: true }
}
}
}
# Throttles the images flowing downstream for flow control. It passes through
# the very first incoming image unaltered, and waits for downstream nodes
# (calculators and subgraphs) in the graph to finish their tasks before it
# passes through another image. All images that come in while waiting are
# dropped, limiting the number of in-flight images in most part of the graph to
# 1. This prevents the downstream nodes from queuing up incoming images and data
# excessively, which leads to increased latency and memory usage, unwanted in
# real-time mobile applications. It also eliminates unnecessarily computation,
# e.g., the output produced by a node may get dropped downstream if the
# subsequent nodes are still busy processing previous inputs.
node {
calculator: "FlowLimiterCalculator"
input_stream: "input_video"
input_stream: "FINISHED:output_video"
input_stream_info: {
tag_index: "FINISHED"
back_edge: true
}
output_stream: "throttled_input_video"
}
# Subgraph that detects poses and corresponding landmarks.
node {
calculator: "PoseLandmarkCpu"
input_side_packet: "ENABLE_SEGMENTATION:enable_segmentation"
input_stream: "IMAGE:throttled_input_video"
output_stream: "LANDMARKS:pose_landmarks"
output_stream: "SEGMENTATION_MASK:segmentation_mask"
output_stream: "DETECTION:pose_detection"
output_stream: "ROI_FROM_LANDMARKS:roi_from_landmarks"
}
# Subgraph that renders pose-landmark annotation onto the input image.
node {
calculator: "PoseRendererCpu"
input_stream: "IMAGE:throttled_input_video"
input_stream: "LANDMARKS:pose_landmarks"
input_stream: "SEGMENTATION_MASK:segmentation_mask"
input_stream: "DETECTION:pose_detection"
input_stream: "ROI:roi_from_landmarks"
output_stream: "IMAGE:output_video"
}