139 lines
4.1 KiB
Protocol Buffer Text Format
139 lines
4.1 KiB
Protocol Buffer Text Format
# MediaPipe Objectron object detection CPU subgraph.
|
|
|
|
type: "ObjectDetectionOidV4Subgraph"
|
|
|
|
input_stream: "IMAGE:input_video"
|
|
input_side_packet: "LABELS_CSV:allowed_labels"
|
|
output_stream: "DETECTIONS:detections"
|
|
|
|
# Transforms the input image on CPU to a 300x300 image. To scale the image, by
|
|
# default it uses the STRETCH scale mode that maps the entire input image to the
|
|
# entire transformed image. As a result, image aspect ratio may be changed and
|
|
# objects in the image may be deformed (stretched or squeezed), but the object
|
|
# detection model used in this graph is agnostic to that deformation.
|
|
node: {
|
|
calculator: "ImageTransformationCalculator"
|
|
input_stream: "IMAGE:input_video"
|
|
output_stream: "IMAGE:transformed_input_video"
|
|
options: {
|
|
[mediapipe.ImageTransformationCalculatorOptions.ext] {
|
|
output_width: 300
|
|
output_height: 300
|
|
}
|
|
}
|
|
}
|
|
|
|
# Converts the transformed input image on CPU into an image tensor stored as a
|
|
# TfLiteTensor.
|
|
node {
|
|
calculator: "TfLiteConverterCalculator"
|
|
input_stream: "IMAGE:transformed_input_video"
|
|
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/models/object_detection_ssd_mobilenetv2_oidv4_fp16.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: 6
|
|
min_scale: 0.2
|
|
max_scale: 0.95
|
|
input_size_height: 300
|
|
input_size_width: 300
|
|
anchor_offset_x: 0.5
|
|
anchor_offset_y: 0.5
|
|
strides: 16
|
|
strides: 32
|
|
strides: 64
|
|
strides: 128
|
|
strides: 256
|
|
strides: 512
|
|
aspect_ratios: 1.0
|
|
aspect_ratios: 2.0
|
|
aspect_ratios: 0.5
|
|
aspect_ratios: 3.0
|
|
aspect_ratios: 0.3333
|
|
reduce_boxes_in_lowest_layer: 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: "TfLiteTensorsToDetectionsCalculator"
|
|
input_stream: "TENSORS:detection_tensors"
|
|
input_side_packet: "ANCHORS:anchors"
|
|
output_stream: "DETECTIONS:all_detections"
|
|
options: {
|
|
[mediapipe.TfLiteTensorsToDetectionsCalculatorOptions.ext] {
|
|
num_classes: 195
|
|
num_boxes: 1917
|
|
num_coords: 4
|
|
ignore_classes: 0
|
|
sigmoid_score: true
|
|
apply_exponential_on_box_size: true
|
|
x_scale: 10.0
|
|
y_scale: 10.0
|
|
h_scale: 5.0
|
|
w_scale: 5.0
|
|
min_score_thresh: 0.5
|
|
}
|
|
}
|
|
}
|
|
|
|
# Maps detection label IDs to the corresponding label text. The label map is
|
|
# provided in the label_map_path option.
|
|
node {
|
|
calculator: "DetectionLabelIdToTextCalculator"
|
|
input_stream: "all_detections"
|
|
output_stream: "labeled_detections"
|
|
options: {
|
|
[mediapipe.DetectionLabelIdToTextCalculatorOptions.ext] {
|
|
label_map_path: "mediapipe/models/object_detection_oidv4_labelmap.pbtxt"
|
|
}
|
|
}
|
|
}
|
|
|
|
# Filters the detections to only those with valid scores
|
|
# for the specified allowed labels.
|
|
node {
|
|
calculator: "FilterDetectionCalculator"
|
|
input_stream: "DETECTIONS:labeled_detections"
|
|
output_stream: "DETECTIONS:filtered_detections"
|
|
input_side_packet: "LABELS_CSV:allowed_labels"
|
|
}
|
|
|
|
# Performs non-max suppression to remove excessive detections.
|
|
node {
|
|
calculator: "NonMaxSuppressionCalculator"
|
|
input_stream: "filtered_detections"
|
|
output_stream: "detections"
|
|
options: {
|
|
[mediapipe.NonMaxSuppressionCalculatorOptions.ext] {
|
|
min_suppression_threshold: 0.5
|
|
max_num_detections: 100
|
|
overlap_type: INTERSECTION_OVER_UNION
|
|
return_empty_detections: true
|
|
}
|
|
}
|
|
}
|