mediapipe/mediapipe2/graphs/youtube8m/local_video_model_inference.pbtxt

input_side_packet: "input_sequence_example_path"
input_side_packet: "input_video_path"
input_side_packet: "output_video_path"
input_side_packet: "segment_size"
input_side_packet: "overlap"

node {
  calculator: "LocalFileContentsCalculator"
  input_side_packet: "FILE_PATH:input_sequence_example_path"
  output_side_packet: "CONTENTS:input_sequence_example"
}

node {
  calculator: "StringToSequenceExampleCalculator"
  input_side_packet: "STRING:input_sequence_example"
  output_side_packet: "SEQUENCE_EXAMPLE:parsed_sequence_example"
}

node {
  calculator: "UnpackMediaSequenceCalculator"
  input_side_packet: "SEQUENCE_EXAMPLE:parsed_sequence_example"
  output_stream: "FLOAT_FEATURE_RGB:rgb_feature_vector"
  output_stream: "FLOAT_FEATURE_AUDIO:audio_feature_vector"
}

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: "StringToInt32Calculator"
  input_side_packet: "segment_size"
  output_side_packet: "segment_size_int"
}

node {
  calculator: "StringToInt32Calculator"
  input_side_packet: "overlap"
  output_side_packet: "overlap_int"
}

node {
  calculator: "LappedTensorBufferCalculator"
  input_stream: "feature_tensor"
  output_stream: "lapped_feature_tensor"
  input_side_packet: "BUFFER_SIZE:segment_size_int"
  input_side_packet: "OVERLAP:overlap_int"
  node_options: {
    [type.googleapis.com/mediapipe.LappedTensorBufferCalculatorOptions] {
      add_batch_dim_to_tensors: true
    }
  }
}

node {
  calculator: "SidePacketToStreamCalculator"
  input_side_packet: "segment_size_int"
  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: "TOP_K_INDEXES:top_k_indexes"
  output_stream: "TOP_K_SCORES:top_k_scores"
  output_stream: "TOP_K_LABELS:top_k_labels"
  node_options: {
    [type.googleapis.com/mediapipe.TopKScoresCalculatorOptions]: {
      top_k: 3
      label_map_path: "mediapipe/graphs/youtube8m/label_map.txt"
    }
  }
}

node {
  calculator: "OpenCvVideoDecoderCalculator"
  input_side_packet: "INPUT_FILE_PATH:input_video_path"
  output_stream: "VIDEO:input_video"
  output_stream: "VIDEO_PRESTREAM:input_video_header"
}

node {
  calculator: "LabelsToRenderDataCalculator"
  input_stream: "LABELS:top_k_labels"
  input_stream: "SCORES:top_k_scores"
  input_stream: "VIDEO_PRESTREAM:input_video_header"
  output_stream: "RENDER_DATA:render_data"
  node_options: {
    [type.googleapis.com/mediapipe.LabelsToRenderDataCalculatorOptions]: {
      color { r: 255 g: 0 b: 0 }
      color { r: 0 g: 255 b: 0 }
      color { r: 0 g: 0 b: 255 }
      thickness: 2.0
      font_height_px: 20
      max_num_labels: 3
      location: TOP_LEFT
    }
  }
}

node {
  calculator: "PacketClonerCalculator"
  input_stream: "render_data"
  input_stream: "input_video"
  output_stream: "synchronized_render_data"
}

node {
  calculator: "AnnotationOverlayCalculator"
  input_stream: "IMAGE:input_video"
  input_stream: "synchronized_render_data"
  output_stream: "IMAGE:output_video"
}

node {
  calculator: "OpenCvVideoEncoderCalculator"
  input_stream: "VIDEO:output_video"
  input_stream: "VIDEO_PRESTREAM:input_video_header"
  input_side_packet: "OUTPUT_FILE_PATH:output_video_path"
  node_options: {
    [type.googleapis.com/mediapipe.OpenCvVideoEncoderCalculatorOptions]: {
      codec: "avc1"
      video_format: "mp4"
    }
  }
}