mediapipe-rs/mediapipe/modules/palm_detection/palm_detection_gpu.pbtxt
2022-06-11 12:25:48 -07:00

154 lines
4.6 KiB
Plaintext

# MediaPipe graph to detect palms with TensorFlow Lite on GPU.
type: "PalmDetectionGpu"
# GPU image. (GpuBuffer)
input_stream: "IMAGE:image"
# Complexity of the palm detection model: 0 or 1. Accuracy as well as inference
# latency generally go up with the model complexity. If unspecified, functions
# as set to 1. (int)
input_side_packet: "MODEL_COMPLEXITY:model_complexity"
# Detected palms. (std::vector<Detection>)
# NOTE: there will not be an output packet in the DETECTIONS stream for this
# particular timestamp if none of palms 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"
# Transforms an image into a 256x256 tensor while keeping the aspect ratio, and
# therefore may result in potential letterboxing.
node {
calculator: "ImageToTensorCalculator"
input_stream: "IMAGE_GPU:image"
output_stream: "TENSORS:input_tensor"
output_stream: "LETTERBOX_PADDING:letterbox_padding"
options: {
[mediapipe.ImageToTensorCalculatorOptions.ext] {
output_tensor_width: 192
output_tensor_height: 192
keep_aspect_ratio: true
output_tensor_float_range {
min: 0.0
max: 1.0
}
border_mode: BORDER_ZERO
gpu_origin: TOP_LEFT
}
}
}
# Generates a single side packet containing a TensorFlow Lite op resolver that
# supports custom ops needed by the model used in this graph.
node {
calculator: "TfLiteCustomOpResolverCalculator"
output_side_packet: "opresolver"
options: {
[mediapipe.TfLiteCustomOpResolverCalculatorOptions.ext] {
use_gpu: true
}
}
}
# Loads the palm detection TF Lite model.
node {
calculator: "PalmDetectionModelLoader"
input_side_packet: "MODEL_COMPLEXITY:model_complexity"
output_side_packet: "MODEL:model"
}
# Runs a TensorFlow Lite model on GPU 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_tensor"
output_stream: "TENSORS:detection_tensors"
input_side_packet: "CUSTOM_OP_RESOLVER:opresolver"
input_side_packet: "MODEL:model"
options: {
[mediapipe.InferenceCalculatorOptions.ext] {
delegate { gpu {} }
}
}
}
# 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: 4
min_scale: 0.1484375
max_scale: 0.75
input_size_width: 192
input_size_height: 192
anchor_offset_x: 0.5
anchor_offset_y: 0.5
strides: 8
strides: 16
strides: 16
strides: 16
aspect_ratios: 1.0
fixed_anchor_size: true
}
}
}
# 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_boxes: 2016
num_coords: 18
box_coord_offset: 0
keypoint_coord_offset: 4
num_keypoints: 7
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
w_scale: 192.0
h_scale: 192.0
min_score_thresh: 0.5
}
}
}
# 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
}
}
}
# 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:detections"
}