140 lines
3.8 KiB
Plaintext
140 lines
3.8 KiB
Plaintext
|
input_side_packet: "desired_segment_size"
|
||
|
|
input_side_packet: "record_index"
|
||
|
|
input_side_packet: "tfrecord_path"
|
||
|
|
output_side_packet: "yt8m_id"
|
||
|
|
output_stream: "annotation_summary"
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "StringToInt32Calculator"
|
||
|
|
input_side_packet: "record_index"
|
||
|
|
output_side_packet: "record_index_int"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "StringToInt32Calculator"
|
||
|
|
input_side_packet: "desired_segment_size"
|
||
|
|
output_side_packet: "desired_segment_size_int"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "TFRecordReaderCalculator"
|
||
|
|
input_side_packet: "TFRECORD_PATH:tfrecord_path"
|
||
|
|
input_side_packet: "RECORD_INDEX:record_index_int"
|
||
|
|
output_side_packet: "SEQUENCE_EXAMPLE:yt8m_sequence_example"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "UnpackYt8mSequenceExampleCalculator"
|
||
|
|
input_side_packet: "YT8M_SEQUENCE_EXAMPLE:yt8m_sequence_example"
|
||
|
|
input_side_packet: "DESIRED_SEGMENT_SIZE:desired_segment_size_int"
|
||
|
|
output_side_packet: "YT8M_ID:yt8m_id"
|
||
|
|
output_side_packet: "SEGMENT_SIZE:segment_size"
|
||
|
|
output_side_packet: "LAPPED_TENSOR_BUFFER_CALCULATOR_OPTIONS:lapped_tensor_buffer_calculator_options"
|
||
|
|
output_stream: "QUANTIZED_RGB_FEATURE:quantized_rgb_feature"
|
||
|
|
output_stream: "QUANTIZED_AUDIO_FEATURE:quantized_audio_feature"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "DequantizeByteArrayCalculator"
|
||
|
|
input_stream: "ENCODED:quantized_rgb_feature"
|
||
|
|
output_stream: "FLOAT_VECTOR:rgb_feature_vector"
|
||
|
|
node_options: {
|
||
|
|
[type.googleapis.com/mediapipe.DequantizeByteArrayCalculatorOptions]: {
|
||
|
|
max_quantized_value: 2
|
||
|
|
min_quantized_value: -2
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "DequantizeByteArrayCalculator"
|
||
|
|
input_stream: "ENCODED:quantized_audio_feature"
|
||
|
|
output_stream: "FLOAT_VECTOR:audio_feature_vector"
|
||
|
|
node_options: {
|
||
|
|
[type.googleapis.com/mediapipe.DequantizeByteArrayCalculatorOptions]: {
|
||
|
|
max_quantized_value: 2
|
||
|
|
min_quantized_value: -2
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "ConcatenateFloatVectorCalculator"
|
||
|
|
input_stream: "rgb_feature_vector"
|
||
|
|
input_stream: "audio_feature_vector"
|
||
|
|
output_stream: "feature_vector"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "VectorFloatToTensorCalculator"
|
||
|
|
input_stream: "feature_vector"
|
||
|
|
output_stream: "feature_tensor"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "LappedTensorBufferCalculator"
|
||
|
|
input_stream: "feature_tensor"
|
||
|
|
input_side_packet: "CALCULATOR_OPTIONS:lapped_tensor_buffer_calculator_options"
|
||
|
|
output_stream: "lapped_feature_tensor"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "SidePacketToStreamCalculator"
|
||
|
|
input_side_packet: "segment_size"
|
||
|
|
output_stream: "AT_ZERO:segment_size_int_stream"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "VectorIntToTensorCalculator"
|
||
|
|
input_stream: "SINGLE_INT:segment_size_int_stream"
|
||
|
|
output_stream: "TENSOR_OUT:segment_size_tensor"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "PacketClonerCalculator"
|
||
|
|
input_stream: "segment_size_tensor"
|
||
|
|
input_stream: "lapped_feature_tensor"
|
||
|
|
output_stream: "synced_segment_size_tensor"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "TensorFlowSessionFromSavedModelCalculator"
|
||
|
|
output_side_packet: "SESSION:session"
|
||
|
|
node_options: {
|
||
|
|
[type.googleapis.com/mediapipe.TensorFlowSessionFromSavedModelCalculatorOptions]: {
|
||
|
|
saved_model_path: "/tmp/mediapipe/saved_model"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
node: {
|
||
|
|
calculator: "TensorFlowInferenceCalculator"
|
||
|
|
input_side_packet: "SESSION:session"
|
||
|
|
input_stream: "NUM_FRAMES:synced_segment_size_tensor"
|
||
|
|
input_stream: "RGB_AND_AUDIO:lapped_feature_tensor"
|
||
|
|
output_stream: "PREDICTIONS:prediction_tensor"
|
||
|
|
node_options: {
|
||
|
|
[type.googleapis.com/mediapipe.TensorFlowInferenceCalculatorOptions]: {
|
||
|
|
batch_size: 32
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "TensorToVectorFloatCalculator"
|
||
|
|
input_stream: "prediction_tensor"
|
||
|
|
output_stream: "prediction_vector"
|
||
|
|
}
|
||
|
|
|
||
|
|
node {
|
||
|
|
calculator: "TopKScoresCalculator"
|
||
|
|
input_stream: "SCORES:prediction_vector"
|
||
|
|
output_stream: "SUMMARY:annotation_summary"
|
||
|
|
node_options: {
|
||
|
|
[type.googleapis.com/mediapipe.TopKScoresCalculatorOptions]: {
|
||
|
|
top_k: 9
|
||
|
|
label_map_path: "mediapipe/graphs/youtube8m/label_map.txt"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|