Project import generated by Copybara.

GitOrigin-RevId: 796203faee20d7aae2876aac8ca5a1827dee4fe3

mediapipe/graphs/face_detection/BUILD

@@ -35,6 +35,23 @@ cc_library(
     ],
 )
 
+cc_library(
+    name = "desktop_tflite_calculators",
+    deps = [
+        "//mediapipe/calculators/core:flow_limiter_calculator",
+        "//mediapipe/calculators/image:image_transformation_calculator",
+        "//mediapipe/calculators/tflite:ssd_anchors_calculator",
+        "//mediapipe/calculators/tflite:tflite_converter_calculator",
+        "//mediapipe/calculators/tflite:tflite_inference_calculator",
+        "//mediapipe/calculators/tflite:tflite_tensors_to_detections_calculator",
+        "//mediapipe/calculators/util:annotation_overlay_calculator",
+        "//mediapipe/calculators/util:detection_label_id_to_text_calculator",
+        "//mediapipe/calculators/util:detection_letterbox_removal_calculator",
+        "//mediapipe/calculators/util:detections_to_render_data_calculator",
+        "//mediapipe/calculators/util:non_max_suppression_calculator",
+    ],
+)
+
 load(
     "//mediapipe/framework/tool:mediapipe_graph.bzl",
     "mediapipe_binary_graph",

mediapipe/graphs/face_detection/face_detection_desktop_live.pbtxt

@@ -0,0 +1,184 @@
+# MediaPipe graph that performs face detection with TensorFlow Lite on CPU.
+# Used in the examples in
+# mediapipie/examples/desktop/face_detection:face_detection_cpu.
+
+# Images on GPU coming into and out of the graph.
+input_stream: "input_video"
+output_stream: "output_video"
+
+# Throttles the images flowing downstream for flow control. It passes through
+# the very first incoming image unaltered, and waits for
+# TfLiteTensorsToDetectionsCalculator downstream in the graph to finish
+# generating the corresponding detections before it passes through another
+# image. All images that come in while waiting are dropped, limiting the number
+# of in-flight images between this calculator and
+# TfLiteTensorsToDetectionsCalculator to 1. This prevents the nodes in between
+# 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., a transformed image produced by
+# ImageTransformationCalculator may get dropped downstream if the subsequent
+# TfLiteConverterCalculator or TfLiteInferenceCalculator is still busy
+# processing previous inputs.
+node {
+  calculator: "FlowLimiterCalculator"
+  input_stream: "input_video"
+  input_stream: "FINISHED:detections"
+  input_stream_info: {
+    tag_index: "FINISHED"
+    back_edge: true
+  }
+  output_stream: "throttled_input_video"
+}
+
+# Transforms the input image on CPU to a 128x128 image. To scale the input
+# image, the scale_mode option is set to FIT to preserve the aspect ratio,
+# resulting in potential letterboxing in the transformed image.
+node: {
+  calculator: "ImageTransformationCalculator"
+  input_stream: "IMAGE:throttled_input_video"
+  output_stream: "IMAGE:transformed_input_video_cpu"
+  output_stream: "LETTERBOX_PADDING:letterbox_padding"
+  node_options: {
+    [type.googleapis.com/mediapipe.ImageTransformationCalculatorOptions] {
+      output_width: 128
+      output_height: 128
+      scale_mode: FIT
+    }
+  }
+}
+
+# Converts the transformed input image on CPU into an image tensor stored as a
+# TfLiteTensor.
+node {
+  calculator: "TfLiteConverterCalculator"
+  input_stream: "IMAGE:transformed_input_video_cpu"
+  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"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
+      model_path: "mediapipe/models/face_detection_front.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"
+  node_options: {
+    [type.googleapis.com/mediapipe.SsdAnchorsCalculatorOptions] {
+      num_layers: 4
+      min_scale: 0.1484375
+      max_scale: 0.75
+      input_size_height: 128
+      input_size_width: 128
+      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: "TfLiteTensorsToDetectionsCalculator"
+  input_stream: "TENSORS:detection_tensors"
+  input_side_packet: "ANCHORS:anchors"
+  output_stream: "DETECTIONS:detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteTensorsToDetectionsCalculatorOptions] {
+      num_classes: 1
+      num_boxes: 896
+      num_coords: 16
+      box_coord_offset: 0
+      keypoint_coord_offset: 4
+      num_keypoints: 6
+      num_values_per_keypoint: 2
+      sigmoid_score: true
+      score_clipping_thresh: 100.0
+      reverse_output_order: true
+      x_scale: 128.0
+      y_scale: 128.0
+      h_scale: 128.0
+      w_scale: 128.0
+      min_score_thresh: 0.75
+    }
+  }
+}
+
+# Performs non-max suppression to remove excessive detections.
+node {
+  calculator: "NonMaxSuppressionCalculator"
+  input_stream: "detections"
+  output_stream: "filtered_detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.NonMaxSuppressionCalculatorOptions] {
+      min_suppression_threshold: 0.3
+      overlap_type: INTERSECTION_OVER_UNION
+      algorithm: WEIGHTED
+      return_empty_detections: true
+    }
+  }
+}
+
+# Maps detection label IDs to the corresponding label text ("Face"). The label
+# map is provided in the label_map_path option.
+node {
+  calculator: "DetectionLabelIdToTextCalculator"
+  input_stream: "filtered_detections"
+  output_stream: "labeled_detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
+      label_map_path: "mediapipe/models/face_detection_front_labelmap.txt"
+    }
+  }
+}
+
+# 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:labeled_detections"
+  input_stream: "LETTERBOX_PADDING:letterbox_padding"
+  output_stream: "DETECTIONS:output_detections"
+}
+
+# Converts the detections to drawing primitives for annotation overlay.
+node {
+  calculator: "DetectionsToRenderDataCalculator"
+  input_stream: "DETECTIONS:output_detections"
+  output_stream: "RENDER_DATA:render_data"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
+      thickness: 4.0
+      color { r: 255 g: 0 b: 0 }
+    }
+  }
+}
+
+# Draws annotations and overlays them on top of the input images.
+node {
+  calculator: "AnnotationOverlayCalculator"
+  input_stream: "INPUT_FRAME:throttled_input_video"
+  input_stream: "render_data"
+  output_stream: "OUTPUT_FRAME:output_video"
+}
+

mediapipe/graphs/face_detection/face_detection_mobile_cpu.pbtxt

@@ -41,7 +41,7 @@ node: {
   output_stream: "input_video_cpu"
 }
 
-# Transforms the input image on GPU to a 128x128 image. To scale the input
+# Transforms the input image on CPU to a 128x128 image. To scale the input
 # image, the scale_mode option is set to FIT to preserve the aspect ratio,
 # resulting in potential letterboxing in the transformed image.
 node: {
@@ -75,7 +75,7 @@ node {
   output_stream: "TENSORS:detection_tensors"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
-      model_path: "face_detection_front.tflite"
+      model_path: "mediapipe/models/face_detection_front.tflite"
     }
   }
 }
@@ -156,7 +156,7 @@ node {
   output_stream: "labeled_detections"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
-      label_map_path: "face_detection_front_labelmap.txt"
+      label_map_path: "mediapipe/models/face_detection_front_labelmap.txt"
     }
   }
 }
@@ -179,7 +179,7 @@ node {
   output_stream: "RENDER_DATA:render_data"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
-      thickness: 10.0
+      thickness: 4.0
       color { r: 255 g: 0 b: 0 }
     }
   }

mediapipe/graphs/face_detection/face_detection_mobile_gpu.pbtxt

@@ -62,10 +62,10 @@ node {
 node {
   calculator: "TfLiteInferenceCalculator"
   input_stream: "TENSORS_GPU:image_tensor"
-  output_stream: "TENSORS:detection_tensors"
+  output_stream: "TENSORS_GPU:detection_tensors"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
-      model_path: "face_detection_front.tflite"
+      model_path: "mediapipe/models/face_detection_front.tflite"
     }
   }
 }
@@ -99,7 +99,7 @@ node {
 # detections. Each detection describes a detected object.
 node {
   calculator: "TfLiteTensorsToDetectionsCalculator"
-  input_stream: "TENSORS:detection_tensors"
+  input_stream: "TENSORS_GPU:detection_tensors"
   input_side_packet: "ANCHORS:anchors"
   output_stream: "DETECTIONS:detections"
   node_options: {
@@ -146,7 +146,7 @@ node {
   output_stream: "labeled_detections"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
-      label_map_path: "face_detection_front_labelmap.txt"
+      label_map_path: "mediapipe/models/face_detection_front_labelmap.txt"
     }
   }
 }
@@ -169,7 +169,7 @@ node {
   output_stream: "RENDER_DATA:render_data"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
-      thickness: 10.0
+      thickness: 4.0
       color { r: 255 g: 0 b: 0 }
     }
   }

mediapipe/graphs/hair_segmentation/hair_segmentation_mobile_gpu.pbtxt

@@ -111,7 +111,7 @@ node {
   input_side_packet: "CUSTOM_OP_RESOLVER:op_resolver"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
-      model_path: "hair_segmentation.tflite"
+      model_path: "mediapipe/models/hair_segmentation.tflite"
       use_gpu: true
     }
   }

mediapipe/graphs/hand_tracking/BUILD

@@ -19,73 +19,35 @@ package(default_visibility = ["//visibility:public"])
 load(
     "//mediapipe/framework/tool:mediapipe_graph.bzl",
     "mediapipe_binary_graph",
-    "mediapipe_simple_subgraph",
 )
 
-mediapipe_simple_subgraph(
-    name = "hand_detection_gpu",
-    graph = "hand_detection_gpu.pbtxt",
-    register_as = "HandDetectionSubgraph",
+cc_library(
+    name = "desktop_tflite_calculators",
     deps = [
-        "//mediapipe/calculators/image:image_properties_calculator",
-        "//mediapipe/calculators/image:image_transformation_calculator",
-        "//mediapipe/calculators/tflite:ssd_anchors_calculator",
-        "//mediapipe/calculators/tflite:tflite_converter_calculator",
-        "//mediapipe/calculators/tflite:tflite_custom_op_resolver_calculator",
-        "//mediapipe/calculators/tflite:tflite_inference_calculator",
-        "//mediapipe/calculators/tflite:tflite_tensors_to_detections_calculator",
-        "//mediapipe/calculators/util:detection_label_id_to_text_calculator",
-        "//mediapipe/calculators/util:detection_letterbox_removal_calculator",
-        "//mediapipe/calculators/util:detections_to_rects_calculator",
-        "//mediapipe/calculators/util:non_max_suppression_calculator",
-        "//mediapipe/calculators/util:rect_transformation_calculator",
-    ],
-)
-
-mediapipe_simple_subgraph(
-    name = "hand_landmark_gpu",
-    graph = "hand_landmark_gpu.pbtxt",
-    register_as = "HandLandmarkSubgraph",
-    deps = [
-        "//mediapipe/calculators/core:split_vector_calculator",
-        "//mediapipe/calculators/image:image_cropping_calculator",
-        "//mediapipe/calculators/image:image_properties_calculator",
-        "//mediapipe/calculators/image:image_transformation_calculator",
-        "//mediapipe/calculators/tflite:tflite_converter_calculator",
-        "//mediapipe/calculators/tflite:tflite_inference_calculator",
-        "//mediapipe/calculators/tflite:tflite_tensors_to_floats_calculator",
-        "//mediapipe/calculators/tflite:tflite_tensors_to_landmarks_calculator",
-        "//mediapipe/calculators/util:detections_to_rects_calculator",
-        "//mediapipe/calculators/util:landmark_letterbox_removal_calculator",
-        "//mediapipe/calculators/util:landmark_projection_calculator",
-        "//mediapipe/calculators/util:landmarks_to_detection_calculator",
-        "//mediapipe/calculators/util:rect_transformation_calculator",
-        "//mediapipe/calculators/util:thresholding_calculator",
-    ],
-)
-
-mediapipe_simple_subgraph(
-    name = "renderer_gpu",
-    graph = "renderer_gpu.pbtxt",
-    register_as = "RendererSubgraph",
-    deps = [
-        "//mediapipe/calculators/util:annotation_overlay_calculator",
-        "//mediapipe/calculators/util:detections_to_render_data_calculator",
-        "//mediapipe/calculators/util:landmarks_to_render_data_calculator",
-        "//mediapipe/calculators/util:rect_to_render_data_calculator",
+        "//mediapipe/calculators/core:flow_limiter_calculator",
+        "//mediapipe/calculators/core:gate_calculator",
+        "//mediapipe/calculators/core:immediate_mux_calculator",
+        "//mediapipe/calculators/core:merge_calculator",
+        "//mediapipe/calculators/core:packet_inner_join_calculator",
+        "//mediapipe/calculators/core:previous_loopback_calculator",
+        "//mediapipe/calculators/video:opencv_video_decoder_calculator",
+        "//mediapipe/calculators/video:opencv_video_encoder_calculator",
+        "//mediapipe/graphs/hand_tracking/subgraphs:hand_detection_cpu",
+        "//mediapipe/graphs/hand_tracking/subgraphs:hand_landmark_cpu",
+        "//mediapipe/graphs/hand_tracking/subgraphs:renderer_cpu",
     ],
 )
 
 cc_library(
     name = "mobile_calculators",
     deps = [
-        ":hand_detection_gpu",
-        ":hand_landmark_gpu",
-        ":renderer_gpu",
         "//mediapipe/calculators/core:flow_limiter_calculator",
         "//mediapipe/calculators/core:gate_calculator",
         "//mediapipe/calculators/core:merge_calculator",
         "//mediapipe/calculators/core:previous_loopback_calculator",
+        "//mediapipe/graphs/hand_tracking/subgraphs:hand_detection_gpu",
+        "//mediapipe/graphs/hand_tracking/subgraphs:hand_landmark_gpu",
+        "//mediapipe/graphs/hand_tracking/subgraphs:renderer_gpu",
     ],
 )
 
@@ -99,9 +61,9 @@ mediapipe_binary_graph(
 cc_library(
     name = "detection_mobile_calculators",
     deps = [
-        ":hand_detection_gpu",
-        ":renderer_gpu",
         "//mediapipe/calculators/core:flow_limiter_calculator",
+        "//mediapipe/graphs/hand_tracking/subgraphs:hand_detection_gpu",
+        "//mediapipe/graphs/hand_tracking/subgraphs:renderer_gpu",
     ],
 )
 

mediapipe/graphs/hand_tracking/hand_detection_desktop.pbtxt

@@ -0,0 +1,62 @@
+# MediaPipe graph that performs hand detection on desktop with TensorFlow Lite
+# on CPU.
+# Used in the example in
+# mediapipie/examples/desktop/hand_tracking:hand_detection_tflite.
+
+# max_queue_size limits the number of packets enqueued on any input stream
+# by throttling inputs to the graph. This makes the graph only process one
+# frame per time.
+max_queue_size: 1
+
+# Decodes an input video file into images and a video header.
+node {
+  calculator: "OpenCvVideoDecoderCalculator"
+  input_side_packet: "INPUT_FILE_PATH:input_video_path"
+  output_stream: "VIDEO:input_video"
+  output_stream: "VIDEO_PRESTREAM:input_video_header"
+}
+
+# Performs hand detection model on the input frames. See
+# hand_detection_cpu.pbtxt for the detail of the sub-graph.
+node {
+  calculator: "HandDetectionSubgraph"
+  input_stream: "input_video"
+  output_stream: "DETECTIONS:output_detections"
+}
+
+# Converts the detections to drawing primitives for annotation overlay.
+node {
+  calculator: "DetectionsToRenderDataCalculator"
+  input_stream: "DETECTIONS:output_detections"
+  output_stream: "RENDER_DATA:render_data"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
+      thickness: 4.0
+      color { r: 0 g: 255 b: 0 }
+    }
+  }
+}
+
+# Draws annotations and overlays them on top of the original image coming into
+# the graph.
+node {
+  calculator: "AnnotationOverlayCalculator"
+  input_stream: "INPUT_FRAME:input_video"
+  input_stream: "render_data"
+  output_stream: "OUTPUT_FRAME:output_video"
+}
+
+# Encodes the annotated images into a video file, adopting properties specified
+# in the input video header, e.g., video framerate.
+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"
+    }
+  }
+}

mediapipe/graphs/hand_tracking/hand_detection_desktop_live.pbtxt

@@ -0,0 +1,38 @@
+# MediaPipe graph that performs hand detection on desktop with TensorFlow Lite
+# on CPU.
+# Used in the example in
+# mediapipie/examples/desktop/hand_tracking:hand_detection_cpu.
+
+# Images coming into and out of the graph.
+input_stream: "input_video"
+output_stream: "output_video"
+
+# Performs hand detection model on the input frames. See
+# hand_detection_cpu.pbtxt for the detail of the sub-graph.
+node {
+  calculator: "HandDetectionSubgraph"
+  input_stream: "input_video"
+  output_stream: "DETECTIONS:output_detections"
+}
+
+# Converts the detections to drawing primitives for annotation overlay.
+node {
+  calculator: "DetectionsToRenderDataCalculator"
+  input_stream: "DETECTIONS:output_detections"
+  output_stream: "RENDER_DATA:render_data"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
+      thickness: 4.0
+      color { r: 0 g: 255 b: 0 }
+    }
+  }
+}
+
+# Draws annotations and overlays them on top of the original image coming into
+# the graph.
+node {
+  calculator: "AnnotationOverlayCalculator"
+  input_stream: "INPUT_FRAME:input_video"
+  input_stream: "render_data"
+  output_stream: "OUTPUT_FRAME:output_video"
+}

mediapipe/graphs/hand_tracking/hand_tracking_desktop.pbtxt

@@ -0,0 +1,126 @@
+# MediaPipe graph that performs hand tracking on desktop with TensorFlow Lite
+# on CPU.
+# Used in the example in
+# mediapipie/examples/desktop/hand_tracking:hand_tracking_tflite.
+
+# max_queue_size limits the number of packets enqueued on any input stream
+# by throttling inputs to the graph. This makes the graph only process one
+# frame per time.
+max_queue_size: 1
+
+# Decodes an input video file into images and a video header.
+node {
+  calculator: "OpenCvVideoDecoderCalculator"
+  input_side_packet: "INPUT_FILE_PATH:input_video_path"
+  output_stream: "VIDEO:input_video"
+  output_stream: "VIDEO_PRESTREAM:input_video_header"
+}
+
+# Caches a hand-presence decision fed back from HandLandmarkSubgraph, and upon
+# the arrival of the next input image sends out the cached decision with the
+# timestamp replaced by that of the input image, essentially generating a packet
+# that carries the previous hand-presence decision. Note that upon the arrival
+# of the very first input image, an empty packet is sent out to jump start the
+# feedback loop.
+node {
+  calculator: "PreviousLoopbackCalculator"
+  input_stream: "MAIN:input_video"
+  input_stream: "LOOP:hand_presence"
+  input_stream_info: {
+    tag_index: "LOOP"
+    back_edge: true
+  }
+  output_stream: "PREV_LOOP:prev_hand_presence"
+}
+
+# Drops the incoming image if HandLandmarkSubgraph was able to identify hand
+# presence in the previous image. Otherwise, passes the incoming image through
+# to trigger a new round of hand detection in HandDetectionSubgraph.
+node {
+  calculator: "GateCalculator"
+  input_stream: "input_video"
+  input_stream: "DISALLOW:prev_hand_presence"
+  output_stream: "hand_detection_input_video"
+
+  node_options: {
+    [type.googleapis.com/mediapipe.GateCalculatorOptions] {
+      empty_packets_as_allow: true
+    }
+  }
+}
+
+# Subgraph that detections hands (see hand_detection_cpu.pbtxt).
+node {
+  calculator: "HandDetectionSubgraph"
+  input_stream: "hand_detection_input_video"
+  output_stream: "DETECTIONS:palm_detections"
+  output_stream: "NORM_RECT:hand_rect_from_palm_detections"
+}
+
+# Subgraph that localizes hand landmarks (see hand_landmark_cpu.pbtxt).
+node {
+  calculator: "HandLandmarkSubgraph"
+  input_stream: "IMAGE:input_video"
+  input_stream: "NORM_RECT:hand_rect"
+  output_stream: "LANDMARKS:hand_landmarks"
+  output_stream: "NORM_RECT:hand_rect_from_landmarks"
+  output_stream: "PRESENCE:hand_presence"
+}
+
+# Caches a hand rectangle fed back from HandLandmarkSubgraph, and upon the
+# arrival of the next input image sends out the cached rectangle with the
+# timestamp replaced by that of the input image, essentially generating a packet
+# that carries the previous hand rectangle. Note that upon the arrival of the
+# very first input image, an empty packet is sent out to jump start the
+# feedback loop.
+node {
+  calculator: "PreviousLoopbackCalculator"
+  input_stream: "MAIN:input_video"
+  input_stream: "LOOP:hand_rect_from_landmarks"
+  input_stream_info: {
+    tag_index: "LOOP"
+    back_edge: true
+  }
+  output_stream: "PREV_LOOP:prev_hand_rect_from_landmarks"
+}
+
+# Merges a stream of hand rectangles generated by HandDetectionSubgraph and that
+# generated by HandLandmarkSubgraph into a single output stream by selecting
+# between one of the two streams. The former is selected if the incoming packet
+# is not empty, i.e., hand detection is performed on the current image by
+# HandDetectionSubgraph (because HandLandmarkSubgraph could not identify hand
+# presence in the previous image). Otherwise, the latter is selected, which is
+# never empty because HandLandmarkSubgraphs processes all images (that went
+# through FlowLimiterCaculator).
+node {
+  calculator: "MergeCalculator"
+  input_stream: "hand_rect_from_palm_detections"
+  input_stream: "prev_hand_rect_from_landmarks"
+  output_stream: "hand_rect"
+}
+
+# Subgraph that renders annotations and overlays them on top of the input
+# images (see renderer_cpu.pbtxt).
+node {
+  calculator: "RendererSubgraph"
+  input_stream: "IMAGE:input_video"
+  input_stream: "LANDMARKS:hand_landmarks"
+  input_stream: "NORM_RECT:hand_rect"
+  input_stream: "DETECTIONS:palm_detections"
+  output_stream: "IMAGE:output_video"
+}
+
+# Encodes the annotated images into a video file, adopting properties specified
+# in the input video header, e.g., video framerate.
+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"
+    }
+  }
+}

mediapipe/graphs/hand_tracking/hand_tracking_desktop_live.pbtxt

@@ -0,0 +1,103 @@
+# MediaPipe graph that performs hand tracking on desktop with TensorFlow Lite
+# on CPU.
+# Used in the example in
+# mediapipie/examples/desktop/hand_tracking:hand_tracking_cpu.
+
+# Images coming into and out of the graph.
+input_stream: "input_video"
+output_stream: "output_video"
+
+# Caches a hand-presence decision fed back from HandLandmarkSubgraph, and upon
+# the arrival of the next input image sends out the cached decision with the
+# timestamp replaced by that of the input image, essentially generating a packet
+# that carries the previous hand-presence decision. Note that upon the arrival
+# of the very first input image, an empty packet is sent out to jump start the
+# feedback loop.
+node {
+  calculator: "PreviousLoopbackCalculator"
+  input_stream: "MAIN:input_video"
+  input_stream: "LOOP:hand_presence"
+  input_stream_info: {
+    tag_index: "LOOP"
+    back_edge: true
+  }
+  output_stream: "PREV_LOOP:prev_hand_presence"
+}
+
+# Drops the incoming image if HandLandmarkSubgraph was able to identify hand
+# presence in the previous image. Otherwise, passes the incoming image through
+# to trigger a new round of hand detection in HandDetectionSubgraph.
+node {
+  calculator: "GateCalculator"
+  input_stream: "input_video"
+  input_stream: "DISALLOW:prev_hand_presence"
+  output_stream: "hand_detection_input_video"
+
+  node_options: {
+    [type.googleapis.com/mediapipe.GateCalculatorOptions] {
+      empty_packets_as_allow: true
+    }
+  }
+}
+
+# Subgraph that detections hands (see hand_detection_cpu.pbtxt).
+node {
+  calculator: "HandDetectionSubgraph"
+  input_stream: "hand_detection_input_video"
+  output_stream: "DETECTIONS:palm_detections"
+  output_stream: "NORM_RECT:hand_rect_from_palm_detections"
+}
+
+# Subgraph that localizes hand landmarks (see hand_landmark_cpu.pbtxt).
+node {
+  calculator: "HandLandmarkSubgraph"
+  input_stream: "IMAGE:input_video"
+  input_stream: "NORM_RECT:hand_rect"
+  output_stream: "LANDMARKS:hand_landmarks"
+  output_stream: "NORM_RECT:hand_rect_from_landmarks"
+  output_stream: "PRESENCE:hand_presence"
+}
+
+# Caches a hand rectangle fed back from HandLandmarkSubgraph, and upon the
+# arrival of the next input image sends out the cached rectangle with the
+# timestamp replaced by that of the input image, essentially generating a packet
+# that carries the previous hand rectangle. Note that upon the arrival of the
+# very first input image, an empty packet is sent out to jump start the
+# feedback loop.
+node {
+  calculator: "PreviousLoopbackCalculator"
+  input_stream: "MAIN:input_video"
+  input_stream: "LOOP:hand_rect_from_landmarks"
+  input_stream_info: {
+    tag_index: "LOOP"
+    back_edge: true
+  }
+  output_stream: "PREV_LOOP:prev_hand_rect_from_landmarks"
+}
+
+# Merges a stream of hand rectangles generated by HandDetectionSubgraph and that
+# generated by HandLandmarkSubgraph into a single output stream by selecting
+# between one of the two streams. The former is selected if the incoming packet
+# is not empty, i.e., hand detection is performed on the current image by
+# HandDetectionSubgraph (because HandLandmarkSubgraph could not identify hand
+# presence in the previous image). Otherwise, the latter is selected, which is
+# never empty because HandLandmarkSubgraphs processes all images (that went
+# through FlowLimiterCaculator).
+node {
+  calculator: "MergeCalculator"
+  input_stream: "hand_rect_from_palm_detections"
+  input_stream: "prev_hand_rect_from_landmarks"
+  output_stream: "hand_rect"
+}
+
+# Subgraph that renders annotations and overlays them on top of the input
+# images (see renderer_cpu.pbtxt).
+node {
+  calculator: "RendererSubgraph"
+  input_stream: "IMAGE:input_video"
+  input_stream: "LANDMARKS:hand_landmarks"
+  input_stream: "NORM_RECT:hand_rect"
+  input_stream: "DETECTIONS:palm_detections"
+  output_stream: "IMAGE:output_video"
+}
+

mediapipe/graphs/hand_tracking/subgraphs/BUILD

@@ -0,0 +1,132 @@
+# Copyright 2019 The MediaPipe Authors.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+licenses(["notice"])  # Apache 2.0
+
+package(default_visibility = ["//visibility:public"])
+
+load(
+    "//mediapipe/framework/tool:mediapipe_graph.bzl",
+    "mediapipe_simple_subgraph",
+)
+
+mediapipe_simple_subgraph(
+    name = "hand_detection_cpu",
+    graph = "hand_detection_cpu.pbtxt",
+    register_as = "HandDetectionSubgraph",
+    deps = [
+        "//mediapipe/calculators/image:image_properties_calculator",
+        "//mediapipe/calculators/image:image_transformation_calculator",
+        "//mediapipe/calculators/tflite:ssd_anchors_calculator",
+        "//mediapipe/calculators/tflite:tflite_converter_calculator",
+        "//mediapipe/calculators/tflite:tflite_custom_op_resolver_calculator",
+        "//mediapipe/calculators/tflite:tflite_inference_calculator",
+        "//mediapipe/calculators/tflite:tflite_tensors_to_detections_calculator",
+        "//mediapipe/calculators/util:detection_label_id_to_text_calculator",
+        "//mediapipe/calculators/util:detection_letterbox_removal_calculator",
+        "//mediapipe/calculators/util:detections_to_rects_calculator",
+        "//mediapipe/calculators/util:detections_to_render_data_calculator",
+        "//mediapipe/calculators/util:non_max_suppression_calculator",
+        "//mediapipe/calculators/util:rect_transformation_calculator",
+    ],
+)
+
+mediapipe_simple_subgraph(
+    name = "hand_landmark_cpu",
+    graph = "hand_landmark_cpu.pbtxt",
+    register_as = "HandLandmarkSubgraph",
+    deps = [
+        "//mediapipe/calculators/core:split_vector_calculator",
+        "//mediapipe/calculators/image:image_cropping_calculator",
+        "//mediapipe/calculators/image:image_properties_calculator",
+        "//mediapipe/calculators/image:image_transformation_calculator",
+        "//mediapipe/calculators/tflite:tflite_converter_calculator",
+        "//mediapipe/calculators/tflite:tflite_inference_calculator",
+        "//mediapipe/calculators/tflite:tflite_tensors_to_floats_calculator",
+        "//mediapipe/calculators/tflite:tflite_tensors_to_landmarks_calculator",
+        "//mediapipe/calculators/util:detections_to_rects_calculator",
+        "//mediapipe/calculators/util:landmark_letterbox_removal_calculator",
+        "//mediapipe/calculators/util:landmark_projection_calculator",
+        "//mediapipe/calculators/util:landmarks_to_detection_calculator",
+        "//mediapipe/calculators/util:landmarks_to_render_data_calculator",
+        "//mediapipe/calculators/util:rect_transformation_calculator",
+        "//mediapipe/calculators/util:thresholding_calculator",
+    ],
+)
+
+mediapipe_simple_subgraph(
+    name = "renderer_cpu",
+    graph = "renderer_cpu.pbtxt",
+    register_as = "RendererSubgraph",
+    deps = [
+        "//mediapipe/calculators/util:annotation_overlay_calculator",
+        "//mediapipe/calculators/util:detections_to_render_data_calculator",
+        "//mediapipe/calculators/util:landmarks_to_render_data_calculator",
+        "//mediapipe/calculators/util:rect_to_render_data_calculator",
+    ],
+)
+
+mediapipe_simple_subgraph(
+    name = "hand_detection_gpu",
+    graph = "hand_detection_gpu.pbtxt",
+    register_as = "HandDetectionSubgraph",
+    deps = [
+        "//mediapipe/calculators/image:image_properties_calculator",
+        "//mediapipe/calculators/image:image_transformation_calculator",
+        "//mediapipe/calculators/tflite:ssd_anchors_calculator",
+        "//mediapipe/calculators/tflite:tflite_converter_calculator",
+        "//mediapipe/calculators/tflite:tflite_custom_op_resolver_calculator",
+        "//mediapipe/calculators/tflite:tflite_inference_calculator",
+        "//mediapipe/calculators/tflite:tflite_tensors_to_detections_calculator",
+        "//mediapipe/calculators/util:detection_label_id_to_text_calculator",
+        "//mediapipe/calculators/util:detection_letterbox_removal_calculator",
+        "//mediapipe/calculators/util:detections_to_rects_calculator",
+        "//mediapipe/calculators/util:non_max_suppression_calculator",
+        "//mediapipe/calculators/util:rect_transformation_calculator",
+    ],
+)
+
+mediapipe_simple_subgraph(
+    name = "hand_landmark_gpu",
+    graph = "hand_landmark_gpu.pbtxt",
+    register_as = "HandLandmarkSubgraph",
+    deps = [
+        "//mediapipe/calculators/core:split_vector_calculator",
+        "//mediapipe/calculators/image:image_cropping_calculator",
+        "//mediapipe/calculators/image:image_properties_calculator",
+        "//mediapipe/calculators/image:image_transformation_calculator",
+        "//mediapipe/calculators/tflite:tflite_converter_calculator",
+        "//mediapipe/calculators/tflite:tflite_inference_calculator",
+        "//mediapipe/calculators/tflite:tflite_tensors_to_floats_calculator",
+        "//mediapipe/calculators/tflite:tflite_tensors_to_landmarks_calculator",
+        "//mediapipe/calculators/util:detections_to_rects_calculator",
+        "//mediapipe/calculators/util:landmark_letterbox_removal_calculator",
+        "//mediapipe/calculators/util:landmark_projection_calculator",
+        "//mediapipe/calculators/util:landmarks_to_detection_calculator",
+        "//mediapipe/calculators/util:rect_transformation_calculator",
+        "//mediapipe/calculators/util:thresholding_calculator",
+    ],
+)
+
+mediapipe_simple_subgraph(
+    name = "renderer_gpu",
+    graph = "renderer_gpu.pbtxt",
+    register_as = "RendererSubgraph",
+    deps = [
+        "//mediapipe/calculators/util:annotation_overlay_calculator",
+        "//mediapipe/calculators/util:detections_to_render_data_calculator",
+        "//mediapipe/calculators/util:landmarks_to_render_data_calculator",
+        "//mediapipe/calculators/util:rect_to_render_data_calculator",
+    ],
+)

mediapipe/graphs/hand_tracking/subgraphs/hand_detection_cpu.pbtxt

@@ -0,0 +1,193 @@
+# MediaPipe hand detection subgraph.
+
+type: "HandDetectionSubgraph"
+
+input_stream: "input_video"
+output_stream: "DETECTIONS:palm_detections"
+output_stream: "NORM_RECT:hand_rect_from_palm_detections"
+
+# Transforms the input image on CPU to a 256x256 image. To scale the input
+# image, the scale_mode option is set to FIT to preserve the aspect ratio,
+# resulting in potential letterboxing in the transformed image.
+node: {
+  calculator: "ImageTransformationCalculator"
+  input_stream: "IMAGE:input_video"
+  output_stream: "IMAGE:transformed_input_video"
+  output_stream: "LETTERBOX_PADDING:letterbox_padding"
+  node_options: {
+    [type.googleapis.com/mediapipe.ImageTransformationCalculatorOptions] {
+      output_width: 256
+      output_height: 256
+      scale_mode: FIT
+    }
+  }
+}
+
+# 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: "op_resolver"
+}
+
+# Converts the transformed input image on CPU into an image tensor as a
+# TfLiteTensor. The zero_center option is set to true to normalize the
+# pixel values to [-1.f, 1.f] as opposed to [0.f, 1.f].
+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"
+  input_side_packet: "CUSTOM_OP_RESOLVER:op_resolver"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
+      model_path: "mediapipe/models/palm_detection.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"
+  node_options: {
+    [type.googleapis.com/mediapipe.SsdAnchorsCalculatorOptions] {
+      num_layers: 5
+      min_scale: 0.1171875
+      max_scale: 0.75
+      input_size_height: 256
+      input_size_width: 256
+      anchor_offset_x: 0.5
+      anchor_offset_y: 0.5
+      strides: 8
+      strides: 16
+      strides: 32
+      strides: 32
+      strides: 32
+      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: "TfLiteTensorsToDetectionsCalculator"
+  input_stream: "TENSORS:detection_tensors"
+  input_side_packet: "ANCHORS:anchors"
+  output_stream: "DETECTIONS:detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteTensorsToDetectionsCalculatorOptions] {
+      num_classes: 1
+      num_boxes: 2944
+      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: 256.0
+      y_scale: 256.0
+      h_scale: 256.0
+      w_scale: 256.0
+      min_score_thresh: 0.5
+    }
+  }
+}
+
+# Performs non-max suppression to remove excessive detections.
+node {
+  calculator: "NonMaxSuppressionCalculator"
+  input_stream: "detections"
+  output_stream: "filtered_detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.NonMaxSuppressionCalculatorOptions] {
+      min_suppression_threshold: 0.3
+      min_score_threshold: 0.5
+      overlap_type: INTERSECTION_OVER_UNION
+      algorithm: WEIGHTED
+      return_empty_detections: true
+    }
+  }
+}
+
+# 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: "filtered_detections"
+  output_stream: "labeled_detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
+      label_map_path: "mediapipe/models/palm_detection_labelmap.txt"
+    }
+  }
+}
+
+# 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:labeled_detections"
+  input_stream: "LETTERBOX_PADDING:letterbox_padding"
+  output_stream: "DETECTIONS:palm_detections"
+}
+
+# Extracts image size from the input images.
+node {
+  calculator: "ImagePropertiesCalculator"
+  input_stream: "IMAGE:input_video"
+  output_stream: "SIZE:image_size"
+}
+
+# Converts results of palm detection into a rectangle (normalized by image size)
+# that encloses the palm and is rotated such that the line connecting center of
+# the wrist and MCP of the middle finger is aligned with the Y-axis of the
+# rectangle.
+node {
+  calculator: "DetectionsToRectsCalculator"
+  input_stream: "DETECTIONS:palm_detections"
+  input_stream: "IMAGE_SIZE:image_size"
+  output_stream: "NORM_RECT:palm_rect"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionsToRectsCalculatorOptions] {
+      rotation_vector_start_keypoint_index: 0  # Center of wrist.
+      rotation_vector_end_keypoint_index: 2  # MCP of middle finger.
+      rotation_vector_target_angle_degrees: 90
+      output_zero_rect_for_empty_detections: true
+    }
+  }
+}
+
+# Expands and shifts the rectangle that contains the palm so that it's likely
+# to cover the entire hand.
+node {
+  calculator: "RectTransformationCalculator"
+  input_stream: "NORM_RECT:palm_rect"
+  input_stream: "IMAGE_SIZE:image_size"
+  output_stream: "hand_rect_from_palm_detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.RectTransformationCalculatorOptions] {
+      scale_x: 2.6
+      scale_y: 2.6
+      shift_y: -0.5
+      square_long: true
+    }
+  }
+}

mediapipe/graphs/hand_tracking/subgraphs/hand_detection_gpu.pbtxt

@@ -49,11 +49,11 @@ node {
 node {
   calculator: "TfLiteInferenceCalculator"
   input_stream: "TENSORS_GPU:image_tensor"
-  output_stream: "TENSORS:detection_tensors"
+  output_stream: "TENSORS_GPU:detection_tensors"
   input_side_packet: "CUSTOM_OP_RESOLVER:opresolver"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
-      model_path: "palm_detection.tflite"
+      model_path: "mediapipe/models/palm_detection.tflite"
       use_gpu: true
     }
   }
@@ -89,7 +89,7 @@ node {
 # detections. Each detection describes a detected object.
 node {
   calculator: "TfLiteTensorsToDetectionsCalculator"
-  input_stream: "TENSORS:detection_tensors"
+  input_stream: "TENSORS_GPU:detection_tensors"
   input_side_packet: "ANCHORS:anchors"
   output_stream: "DETECTIONS:detections"
   node_options: {
@@ -137,7 +137,7 @@ node {
   output_stream: "labeled_detections"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
-      label_map_path: "palm_detection_labelmap.txt"
+      label_map_path: "mediapipe/models/palm_detection_labelmap.txt"
     }
   }
 }

mediapipe/graphs/hand_tracking/subgraphs/hand_landmark_cpu.pbtxt

@@ -0,0 +1,185 @@
+# MediaPipe hand landmark localization subgraph.
+
+type: "HandLandmarkSubgraph"
+
+input_stream: "IMAGE:input_video"
+input_stream: "NORM_RECT:hand_rect"
+output_stream: "LANDMARKS:hand_landmarks"
+output_stream: "NORM_RECT:hand_rect_for_next_frame"
+output_stream: "PRESENCE:hand_presence"
+
+# Crops the rectangle that contains a hand from the input image.
+node {
+  calculator: "ImageCroppingCalculator"
+  input_stream: "IMAGE:input_video"
+  input_stream: "NORM_RECT:hand_rect"
+  output_stream: "IMAGE:hand_image"
+}
+
+# Transforms the input image on CPU to a 256x256 image. To scale the input
+# image, the scale_mode option is set to FIT to preserve the aspect ratio,
+# resulting in potential letterboxing in the transformed image.
+node: {
+  calculator: "ImageTransformationCalculator"
+  input_stream: "IMAGE:hand_image"
+  output_stream: "IMAGE:transformed_input_video"
+  output_stream: "LETTERBOX_PADDING:letterbox_padding"
+  node_options: {
+    [type.googleapis.com/mediapipe.ImageTransformationCalculatorOptions] {
+      output_width: 256
+      output_height: 256
+      scale_mode: FIT
+    }
+  }
+}
+
+# Converts the transformed input image on GPU into an image tensor stored in
+# tflite::gpu::GlBuffer. The zero_center option is set to true to normalize the
+# pixel values to [-1.f, 1.f] as opposed to [0.f, 1.f]. The flip_vertically
+# option is set to true to account for the descrepancy between the
+# representation of the input image (origin at the bottom-left corner, the
+# OpenGL convention) and what the model used in this graph is expecting (origin
+# at the top-left corner).
+node {
+  calculator: "TfLiteConverterCalculator"
+  input_stream: "IMAGE:transformed_input_video"
+  output_stream: "TENSORS:image_tensor"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteConverterCalculatorOptions] {
+      zero_center: false
+    }
+  }
+}
+
+# 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: "TfLiteInferenceCalculator"
+  input_stream: "TENSORS:image_tensor"
+  output_stream: "TENSORS:output_tensors"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
+      model_path: "mediapipe/models/hand_landmark.tflite"
+    }
+  }
+}
+
+# Splits a vector of TFLite tensors to multiple vectors according to the ranges
+# specified in option.
+node {
+  calculator: "SplitTfLiteTensorVectorCalculator"
+  input_stream: "output_tensors"
+  output_stream: "landmark_tensors"
+  output_stream: "hand_flag_tensor"
+  node_options: {
+    [type.googleapis.com/mediapipe.SplitVectorCalculatorOptions] {
+      ranges: { begin: 0 end: 1 }
+      ranges: { begin: 1 end: 2 }
+    }
+  }
+}
+
+# Converts the hand-flag tensor into a float that represents the confidence
+# score of hand presence.
+node {
+  calculator: "TfLiteTensorsToFloatsCalculator"
+  input_stream: "TENSORS:hand_flag_tensor"
+  output_stream: "FLOAT:hand_presence_score"
+}
+
+# Applies a threshold to the confidence score to determine whether a hand is
+# present.
+node {
+  calculator: "ThresholdingCalculator"
+  input_stream: "FLOAT:hand_presence_score"
+  output_stream: "FLAG:hand_presence"
+  node_options: {
+    [type.googleapis.com/mediapipe.ThresholdingCalculatorOptions] {
+      threshold: 0.1
+    }
+  }
+}
+
+# Decodes the landmark tensors into a vector of lanmarks, where the landmark
+# coordinates are normalized by the size of the input image to the model.
+node {
+  calculator: "TfLiteTensorsToLandmarksCalculator"
+  input_stream: "TENSORS:landmark_tensors"
+  output_stream: "NORM_LANDMARKS:landmarks"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteTensorsToLandmarksCalculatorOptions] {
+      num_landmarks: 21
+      input_image_width: 256
+      input_image_height: 256
+    }
+  }
+}
+
+# Adjusts landmarks (already normalized to [0.f, 1.f]) on the letterboxed hand
+# image (after image transformation with the FIT scale mode) to the
+# corresponding locations on the same image with the letterbox removed (hand
+# image before image transformation).
+node {
+  calculator: "LandmarkLetterboxRemovalCalculator"
+  input_stream: "LANDMARKS:landmarks"
+  input_stream: "LETTERBOX_PADDING:letterbox_padding"
+  output_stream: "LANDMARKS:scaled_landmarks"
+}
+
+# Projects the landmarks from the cropped hand image to the corresponding
+# locations on the full image before cropping (input to the graph).
+node {
+  calculator: "LandmarkProjectionCalculator"
+  input_stream: "NORM_LANDMARKS:scaled_landmarks"
+  input_stream: "NORM_RECT:hand_rect"
+  output_stream: "NORM_LANDMARKS:hand_landmarks"
+}
+
+# Extracts image size from the input images.
+node {
+  calculator: "ImagePropertiesCalculator"
+  input_stream: "IMAGE:input_video"
+  output_stream: "SIZE:image_size"
+}
+
+# Converts hand landmarks to a detection that tightly encloses all landmarks.
+node {
+  calculator: "LandmarksToDetectionCalculator"
+  input_stream: "NORM_LANDMARKS:hand_landmarks"
+  output_stream: "DETECTION:hand_detection"
+}
+
+# Converts the hand detection into a rectangle (normalized by image size)
+# that encloses the hand and is rotated such that the line connecting center of
+# the wrist and MCP of the middle finger is aligned with the Y-axis of the
+# rectangle.
+node {
+  calculator: "DetectionsToRectsCalculator"
+  input_stream: "DETECTION:hand_detection"
+  input_stream: "IMAGE_SIZE:image_size"
+  output_stream: "NORM_RECT:hand_rect_from_landmarks"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionsToRectsCalculatorOptions] {
+      rotation_vector_start_keypoint_index: 0  # Center of wrist.
+      rotation_vector_end_keypoint_index: 9  # MCP of middle finger.
+      rotation_vector_target_angle_degrees: 90
+    }
+  }
+}
+
+# Expands the hand rectangle so that in the next video frame it's likely to
+# still contain the hand even with some motion.
+node {
+  calculator: "RectTransformationCalculator"
+  input_stream: "NORM_RECT:hand_rect_from_landmarks"
+  input_stream: "IMAGE_SIZE:image_size"
+  output_stream: "hand_rect_for_next_frame"
+  node_options: {
+    [type.googleapis.com/mediapipe.RectTransformationCalculatorOptions] {
+      scale_x: 1.6
+      scale_y: 1.6
+      square_long: true
+    }
+  }
+}

mediapipe/graphs/hand_tracking/subgraphs/hand_landmark_gpu.pbtxt

@@ -39,6 +39,11 @@ node {
   calculator: "TfLiteConverterCalculator"
   input_stream: "IMAGE_GPU:transformed_hand_image"
   output_stream: "TENSORS_GPU:image_tensor"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteConverterCalculatorOptions] {
+      zero_center: false
+    }
+  }
 }
 
 # Runs a TensorFlow Lite model on GPU that takes an image tensor and outputs a
@@ -50,7 +55,7 @@ node {
   output_stream: "TENSORS:output_tensors"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
-      model_path: "hand_landmark.tflite"
+      model_path: "mediapipe/models/hand_landmark.tflite"
       use_gpu: true
     }
   }

mediapipe/graphs/hand_tracking/subgraphs/renderer_cpu.pbtxt

@@ -0,0 +1,102 @@
+# MediaPipe hand tracking rendering subgraph.
+
+type: "RendererSubgraph"
+
+input_stream: "IMAGE:input_image"
+input_stream: "DETECTIONS:detections"
+input_stream: "LANDMARKS:landmarks"
+input_stream: "NORM_RECT:rect"
+output_stream: "IMAGE:output_image"
+
+# Converts detections to drawing primitives for annotation overlay.
+node {
+  calculator: "DetectionsToRenderDataCalculator"
+  input_stream: "DETECTIONS:detections"
+  output_stream: "RENDER_DATA:detection_render_data"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
+      thickness: 4.0
+      color { r: 0 g: 255 b: 0 }
+    }
+  }
+}
+
+# Converts landmarks to drawing primitives for annotation overlay.
+node {
+  calculator: "LandmarksToRenderDataCalculator"
+  input_stream: "NORM_LANDMARKS:landmarks"
+  output_stream: "RENDER_DATA:landmark_render_data"
+  node_options: {
+    [type.googleapis.com/mediapipe.LandmarksToRenderDataCalculatorOptions] {
+      landmark_connections: 0
+      landmark_connections: 1
+      landmark_connections: 1
+      landmark_connections: 2
+      landmark_connections: 2
+      landmark_connections: 3
+      landmark_connections: 3
+      landmark_connections: 4
+      landmark_connections: 0
+      landmark_connections: 5
+      landmark_connections: 5
+      landmark_connections: 6
+      landmark_connections: 6
+      landmark_connections: 7
+      landmark_connections: 7
+      landmark_connections: 8
+      landmark_connections: 5
+      landmark_connections: 9
+      landmark_connections: 9
+      landmark_connections: 10
+      landmark_connections: 10
+      landmark_connections: 11
+      landmark_connections: 11
+      landmark_connections: 12
+      landmark_connections: 9
+      landmark_connections: 13
+      landmark_connections: 13
+      landmark_connections: 14
+      landmark_connections: 14
+      landmark_connections: 15
+      landmark_connections: 15
+      landmark_connections: 16
+      landmark_connections: 13
+      landmark_connections: 17
+      landmark_connections: 0
+      landmark_connections: 17
+      landmark_connections: 17
+      landmark_connections: 18
+      landmark_connections: 18
+      landmark_connections: 19
+      landmark_connections: 19
+      landmark_connections: 20
+      landmark_color { r: 255 g: 0 b: 0 }
+      connection_color { r: 0 g: 255 b: 0 }
+      thickness: 4.0
+    }
+  }
+}
+
+# Converts normalized rects to drawing primitives for annotation overlay.
+node {
+  calculator: "RectToRenderDataCalculator"
+  input_stream: "NORM_RECT:rect"
+  output_stream: "RENDER_DATA:rect_render_data"
+  node_options: {
+    [type.googleapis.com/mediapipe.RectToRenderDataCalculatorOptions] {
+      filled: false
+      color { r: 255 g: 0 b: 0 }
+      thickness: 4.0
+    }
+  }
+}
+
+# Draws annotations and overlays them on top of the input images.
+node {
+  calculator: "AnnotationOverlayCalculator"
+  input_stream: "INPUT_FRAME:input_image"
+  input_stream: "detection_render_data"
+  input_stream: "landmark_render_data"
+  input_stream: "rect_render_data"
+  output_stream: "OUTPUT_FRAME:output_image"
+}

mediapipe/graphs/object_detection/BUILD

@@ -56,6 +56,10 @@ cc_library(
 cc_library(
     name = "desktop_tflite_calculators",
     deps = [
+        "//mediapipe/calculators/core:concatenate_vector_calculator",
+        "//mediapipe/calculators/core:flow_limiter_calculator",
+        "//mediapipe/calculators/core:previous_loopback_calculator",
+        "//mediapipe/calculators/core:split_vector_calculator",
         "//mediapipe/calculators/image:image_transformation_calculator",
         "//mediapipe/calculators/tflite:ssd_anchors_calculator",
         "//mediapipe/calculators/tflite:tflite_converter_calculator",

mediapipe/graphs/object_detection/object_detection_desktop_live.pbtxt

@@ -0,0 +1,174 @@
+# MediaPipe graph that performs object detection with TensorFlow Lite on CPU.
+# Used in the examples in
+# mediapipie/examples/desktop/object_detection:object_detection_cpu.
+
+# Images on CPU coming into and out of the graph.
+input_stream: "input_video"
+output_stream: "output_video"
+
+# Throttles the images flowing downstream for flow control. It passes through
+# the very first incoming image unaltered, and waits for
+# TfLiteTensorsToDetectionsCalculator downstream in the graph to finish
+# generating the corresponding detections before it passes through another
+# image. All images that come in while waiting are dropped, limiting the number
+# of in-flight images between this calculator and
+# TfLiteTensorsToDetectionsCalculator to 1. This prevents the nodes in between
+# 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., a transformed image produced by
+# ImageTransformationCalculator may get dropped downstream if the subsequent
+# TfLiteConverterCalculator or TfLiteInferenceCalculator is still busy
+# processing previous inputs.
+node {
+  calculator: "FlowLimiterCalculator"
+  input_stream: "input_video"
+  input_stream: "FINISHED:detections"
+  input_stream_info: {
+    tag_index: "FINISHED"
+    back_edge: true
+  }
+  output_stream: "throttled_input_video"
+}
+
+# Transforms the input image on CPU to a 320x320 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:throttled_input_video"
+  output_stream: "IMAGE:transformed_input_video"
+  node_options: {
+    [type.googleapis.com/mediapipe.ImageTransformationCalculatorOptions] {
+      output_width: 320
+      output_height: 320
+    }
+  }
+}
+
+# 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"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
+      model_path: "mediapipe/models/ssdlite_object_detection.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"
+  node_options: {
+    [type.googleapis.com/mediapipe.SsdAnchorsCalculatorOptions] {
+      num_layers: 6
+      min_scale: 0.2
+      max_scale: 0.95
+      input_size_height: 320
+      input_size_width: 320
+      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:detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteTensorsToDetectionsCalculatorOptions] {
+      num_classes: 91
+      num_boxes: 2034
+      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: 0.6
+    }
+  }
+}
+
+# Performs non-max suppression to remove excessive detections.
+node {
+  calculator: "NonMaxSuppressionCalculator"
+  input_stream: "detections"
+  output_stream: "filtered_detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.NonMaxSuppressionCalculatorOptions] {
+      min_suppression_threshold: 0.4
+      max_num_detections: 3
+      overlap_type: INTERSECTION_OVER_UNION
+      return_empty_detections: true
+    }
+  }
+}
+
+# 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: "filtered_detections"
+  output_stream: "output_detections"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
+      label_map_path: "mediapipe/models/ssdlite_object_detection_labelmap.txt"
+    }
+  }
+}
+
+# Converts the detections to drawing primitives for annotation overlay.
+node {
+  calculator: "DetectionsToRenderDataCalculator"
+  input_stream: "DETECTIONS:output_detections"
+  output_stream: "RENDER_DATA:render_data"
+  node_options: {
+    [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
+      thickness: 4.0
+      color { r: 255 g: 0 b: 0 }
+    }
+  }
+}
+
+# Draws annotations and overlays them on top of the input images.
+node {
+  calculator: "AnnotationOverlayCalculator"
+  input_stream: "INPUT_FRAME:throttled_input_video"
+  input_stream: "render_data"
+  output_stream: "OUTPUT_FRAME:output_video"
+}

mediapipe/graphs/object_detection/object_detection_mobile_cpu.pbtxt

@@ -75,7 +75,7 @@ node {
   output_stream: "TENSORS:detection_tensors"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
-      model_path: "ssdlite_object_detection.tflite"
+      model_path: "mediapipe/models/ssdlite_object_detection.tflite"
     }
   }
 }
@@ -158,7 +158,7 @@ node {
   output_stream: "output_detections"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
-      label_map_path: "ssdlite_object_detection_labelmap.txt"
+      label_map_path: "mediapipe/models/ssdlite_object_detection_labelmap.txt"
     }
   }
 }

mediapipe/graphs/object_detection/object_detection_mobile_gpu.pbtxt

@@ -62,10 +62,10 @@ node {
 node {
   calculator: "TfLiteInferenceCalculator"
   input_stream: "TENSORS_GPU:image_tensor"
-  output_stream: "TENSORS:detection_tensors"
+  output_stream: "TENSORS_GPU:detection_tensors"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
-      model_path: "ssdlite_object_detection.tflite"
+      model_path: "mediapipe/models/ssdlite_object_detection.tflite"
     }
   }
 }
@@ -105,7 +105,7 @@ node {
 # detections. Each detection describes a detected object.
 node {
   calculator: "TfLiteTensorsToDetectionsCalculator"
-  input_stream: "TENSORS:detection_tensors"
+  input_stream: "TENSORS_GPU:detection_tensors"
   input_side_packet: "ANCHORS:anchors"
   output_stream: "DETECTIONS:detections"
   node_options: {
@@ -148,7 +148,7 @@ node {
   output_stream: "output_detections"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
-      label_map_path: "ssdlite_object_detection_labelmap.txt"
+      label_map_path: "mediapipe/models/ssdlite_object_detection_labelmap.txt"
     }
   }
 }

mediapipe/graphs/youtube8m/BUILD

@@ -17,7 +17,7 @@ licenses(["notice"])  # Apache 2.0
 package(default_visibility = ["//visibility:public"])
 
 cc_library(
-    name = "yt8m_calculators_deps",
+    name = "yt8m_feature_extraction_calculators",
     deps = [
         "//mediapipe/calculators/audio:audio_decoder_calculator",
         "//mediapipe/calculators/audio:basic_time_series_calculators",

mediapipe/graphs/youtube8m/feature_extraction.pbtxt

@@ -16,12 +16,16 @@ node {
   input_side_packet: "SEQUENCE_EXAMPLE:parsed_sequence_example"
   output_side_packet: "DATA_PATH:input_file"
   output_side_packet: "RESAMPLER_OPTIONS:packet_resampler_options"
+  output_side_packet: "AUDIO_DECODER_OPTIONS:audio_decoder_options"
   node_options: {
     [type.googleapis.com/mediapipe.UnpackMediaSequenceCalculatorOptions]: {
       base_packet_resampler_options {
         frame_rate: 1.0
         base_timestamp: 0
       }
+      base_audio_decoder_options {
+        audio_stream { stream_index: 0 }
+      }
     }
   }
 }
@@ -121,13 +125,9 @@ node {
 node {
   calculator: "AudioDecoderCalculator"
   input_side_packet: "INPUT_FILE_PATH:input_file"
+  input_side_packet: "OPTIONS:audio_decoder_options"
   output_stream: "AUDIO:audio"
   output_stream: "AUDIO_HEADER:audio_header"
-  node_options: {
-    [type.googleapis.com/mediapipe.AudioDecoderOptions]: {
-      audio_stream { stream_index: 0 }
-    }
-  }
 }
 
 node {