Project import generated by Copybara.

PiperOrigin-RevId: 263889205

mediapipe/graphs/edge_detection/BUILD

@@ -1,4 +1,4 @@
-# Copyright 2019 The MediaPipeOSS Authors.
+# 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.
@@ -11,14 +11,13 @@
 # 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"])
 
 cc_library(
-    name = "android_calculators",
+    name = "mobile_calculators",
     deps = [
         "//mediapipe/calculators/image:luminance_calculator",
         "//mediapipe/calculators/image:sobel_edges_calculator",
@@ -31,7 +30,7 @@ load(
 )
 
 mediapipe_binary_graph(
-    name = "android_gpu_binary_graph",
-    graph = "edge_detection_android_gpu.pbtxt",
-    output_name = "android_gpu.binarypb",
+    name = "mobile_gpu_binary_graph",
+    graph = "edge_detection_mobile_gpu.pbtxt",
+    output_name = "mobile_gpu.binarypb",
 )

mediapipe/graphs/edge_detection/edge_detection_mobile_gpu.pbtxt

@@ -1,6 +1,7 @@
-# MediaPipe graph that performs Sobel edge detection on a live video stream on
-# GPU. Used in the example in
-# mediapipe/examples/android/src/java/com/mediapipe/apps/edgedetectiongpu.
+# MediaPipe graph that performs GPU Sobel edge detection on a live video stream.
+# Used in the examples in
+# mediapipe/examples/android/src/java/com/mediapipe/apps/edgedetectiongpu and
+# mediapipe/examples/ios/edgedetectiongpu.
 
 # Images coming into and out of the graph.
 input_stream: "input_video"

mediapipe/graphs/face_detection/BUILD

@@ -1,4 +1,4 @@
-# Copyright 2019 The MediaPipeOSS Authors.
+# 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.
@@ -11,16 +11,15 @@
 # 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"])
 
 cc_library(
-    name = "android_calculators",
+    name = "mobile_calculators",
     deps = [
-        "//mediapipe/calculators/core:real_time_flow_limiter_calculator",
+        "//mediapipe/calculators/core:flow_limiter_calculator",
         "//mediapipe/calculators/image:image_transformation_calculator",
         "//mediapipe/calculators/tflite:ssd_anchors_calculator",
         "//mediapipe/calculators/tflite:tflite_converter_calculator",
@@ -42,37 +41,15 @@ load(
 )
 
 mediapipe_binary_graph(
-    name = "android_cpu_binary_graph",
-    graph = "face_detection_android_cpu.pbtxt",
-    output_name = "android_cpu.binarypb",
-    deps = [
-        "//mediapipe/calculators/image:image_transformation_calculator_proto",
-        "//mediapipe/calculators/image:scale_image_calculator_proto",
-        "//mediapipe/calculators/tflite:ssd_anchors_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_converter_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_inference_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_tensors_to_detections_calculator_proto",
-        "//mediapipe/calculators/util:annotation_overlay_calculator_proto",
-        "//mediapipe/calculators/util:detection_label_id_to_text_calculator_proto",
-        "//mediapipe/calculators/util:detections_to_render_data_calculator_proto",
-        "//mediapipe/calculators/util:non_max_suppression_calculator_proto",
-    ],
+    name = "mobile_cpu_binary_graph",
+    graph = "face_detection_mobile_cpu.pbtxt",
+    output_name = "mobile_cpu.binarypb",
+    deps = [":mobile_calculators"],
 )
 
 mediapipe_binary_graph(
-    name = "android_gpu_binary_graph",
-    graph = "face_detection_android_gpu.pbtxt",
-    output_name = "android_gpu.binarypb",
-    deps = [
-        "//mediapipe/calculators/image:image_transformation_calculator_proto",
-        "//mediapipe/calculators/image:scale_image_calculator_proto",
-        "//mediapipe/calculators/tflite:ssd_anchors_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_converter_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_inference_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_tensors_to_detections_calculator_proto",
-        "//mediapipe/calculators/util:annotation_overlay_calculator_proto",
-        "//mediapipe/calculators/util:detection_label_id_to_text_calculator_proto",
-        "//mediapipe/calculators/util:detections_to_render_data_calculator_proto",
-        "//mediapipe/calculators/util:non_max_suppression_calculator_proto",
-    ],
+    name = "mobile_gpu_binary_graph",
+    graph = "face_detection_mobile_gpu.pbtxt",
+    output_name = "mobile_gpu.binarypb",
+    deps = [":mobile_calculators"],
 )

mediapipe/graphs/face_detection/face_detection_mobile_cpu.pbtxt

@@ -1,6 +1,7 @@
 # MediaPipe graph that performs face detection with TensorFlow Lite on CPU.
-# Used in the example in
-# mediapipie/examples/android/src/java/com/mediapipe/apps/facedetectioncpu.
+# Used in the examples in
+# mediapipie/examples/android/src/java/com/mediapipe/apps/facedetectioncpu and
+# mediapipie/examples/ios/facedetectioncpu.
 
 # Images on GPU coming into and out of the graph.
 input_stream: "input_video"
@@ -20,7 +21,7 @@ output_stream: "output_video"
 # TfLiteConverterCalculator or TfLiteInferenceCalculator is still busy
 # processing previous inputs.
 node {
-  calculator: "RealTimeFlowLimiterCalculator"
+  calculator: "FlowLimiterCalculator"
   input_stream: "input_video"
   input_stream: "FINISHED:detections"
   input_stream_info: {
@@ -57,22 +58,12 @@ node: {
   }
 }
 
-# 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]. 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) and what
-# the model used in this graph is expecting (origin at the top-left corner).
+# 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"
-  node_options: {
-    [type.googleapis.com/mediapipe.TfLiteConverterCalculatorOptions] {
-      zero_center: true
-      flip_vertically: true
-    }
-  }
 }
 
 # Runs a TensorFlow Lite model on CPU that takes an image tensor and outputs a
@@ -84,7 +75,7 @@ node {
   output_stream: "TENSORS:detection_tensors"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
-      model_path: "facedetector_front.tflite"
+      model_path: "face_detection_front.tflite"
     }
   }
 }
@@ -137,7 +128,7 @@ node {
       y_scale: 128.0
       h_scale: 128.0
       w_scale: 128.0
-      flip_vertically: true
+      min_score_thresh: 0.75
     }
   }
 }
@@ -150,9 +141,9 @@ node {
   node_options: {
     [type.googleapis.com/mediapipe.NonMaxSuppressionCalculatorOptions] {
       min_suppression_threshold: 0.3
-      min_score_threshold: 0.75
       overlap_type: INTERSECTION_OVER_UNION
       algorithm: WEIGHTED
+      return_empty_detections: true
     }
   }
 }
@@ -165,7 +156,7 @@ node {
   output_stream: "labeled_detections"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
-      label_map_path: "facedetector_front_labelmap.txt"
+      label_map_path: "face_detection_front_labelmap.txt"
     }
   }
 }
@@ -184,7 +175,7 @@ node {
 # Converts the detections to drawing primitives for annotation overlay.
 node {
   calculator: "DetectionsToRenderDataCalculator"
-  input_stream: "DETECTION_VECTOR:output_detections"
+  input_stream: "DETECTIONS:output_detections"
   output_stream: "RENDER_DATA:render_data"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
@@ -194,21 +185,12 @@ node {
   }
 }
 
-# Draws annotations and overlays them on top of the CPU copy of the original
-# image coming into the graph. The calculator assumes that image origin is
-# always at the top-left corner and renders text accordingly. However, the input
-# image has its origin at the bottom-left corner (OpenGL convention) and the
-# flip_text_vertically option is set to true to compensate that.
+# Draws annotations and overlays them on top of the input images.
 node {
   calculator: "AnnotationOverlayCalculator"
   input_stream: "INPUT_FRAME:input_video_cpu"
   input_stream: "render_data"
   output_stream: "OUTPUT_FRAME:output_video_cpu"
-  node_options: {
-    [type.googleapis.com/mediapipe.AnnotationOverlayCalculatorOptions] {
-      flip_text_vertically: true
-    }
-  }
 }
 
 # Transfers the annotated image from CPU back to GPU memory, to be sent out of

mediapipe/graphs/face_detection/face_detection_mobile_gpu.pbtxt

@@ -1,6 +1,7 @@
 # MediaPipe graph that performs face detection with TensorFlow Lite on GPU.
-# Used in the example in
-# mediapipie/examples/android/src/java/com/mediapipe/apps/facedetectiongpu.
+# Used in the examples in
+# mediapipie/examples/android/src/java/com/mediapipe/apps/facedetectiongpu and
+# mediapipie/examples/ios/facedetectiongpu.
 
 # Images on GPU coming into and out of the graph.
 input_stream: "input_video"
@@ -20,7 +21,7 @@ output_stream: "output_video"
 # TfLiteConverterCalculator or TfLiteInferenceCalculator is still busy
 # processing previous inputs.
 node {
-  calculator: "RealTimeFlowLimiterCalculator"
+  calculator: "FlowLimiterCalculator"
   input_stream: "input_video"
   input_stream: "FINISHED:detections"
   input_stream_info: {
@@ -47,23 +48,12 @@ node: {
   }
 }
 
-# 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).
+# Converts the transformed input image on GPU into an image tensor stored as a
+# TfLiteTensor.
 node {
   calculator: "TfLiteConverterCalculator"
   input_stream: "IMAGE_GPU:transformed_input_video"
   output_stream: "TENSORS_GPU:image_tensor"
-  node_options: {
-    [type.googleapis.com/mediapipe.TfLiteConverterCalculatorOptions] {
-      zero_center: true
-      flip_vertically: true
-    }
-  }
 }
 
 # Runs a TensorFlow Lite model on GPU that takes an image tensor and outputs a
@@ -72,10 +62,10 @@ node {
 node {
   calculator: "TfLiteInferenceCalculator"
   input_stream: "TENSORS_GPU:image_tensor"
-  output_stream: "TENSORS_GPU:detection_tensors"
+  output_stream: "TENSORS:detection_tensors"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
-      model_path: "facedetector_front.tflite"
+      model_path: "face_detection_front.tflite"
     }
   }
 }
@@ -109,7 +99,7 @@ node {
 # detections. Each detection describes a detected object.
 node {
   calculator: "TfLiteTensorsToDetectionsCalculator"
-  input_stream: "TENSORS_GPU:detection_tensors"
+  input_stream: "TENSORS:detection_tensors"
   input_side_packet: "ANCHORS:anchors"
   output_stream: "DETECTIONS:detections"
   node_options: {
@@ -128,7 +118,7 @@ node {
       y_scale: 128.0
       h_scale: 128.0
       w_scale: 128.0
-      flip_vertically: true
+      min_score_thresh: 0.75
     }
   }
 }
@@ -141,9 +131,9 @@ node {
   node_options: {
     [type.googleapis.com/mediapipe.NonMaxSuppressionCalculatorOptions] {
       min_suppression_threshold: 0.3
-      min_score_threshold: 0.75
       overlap_type: INTERSECTION_OVER_UNION
       algorithm: WEIGHTED
+      return_empty_detections: true
     }
   }
 }
@@ -156,7 +146,7 @@ node {
   output_stream: "labeled_detections"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionLabelIdToTextCalculatorOptions] {
-      label_map_path: "facedetector_front_labelmap.txt"
+      label_map_path: "face_detection_front_labelmap.txt"
     }
   }
 }
@@ -175,31 +165,20 @@ node {
 # Converts the detections to drawing primitives for annotation overlay.
 node {
   calculator: "DetectionsToRenderDataCalculator"
-  input_stream: "DETECTION_VECTOR:output_detections"
+  input_stream: "DETECTIONS:output_detections"
   output_stream: "RENDER_DATA:render_data"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
-      thickness: 8.0
+      thickness: 10.0
       color { r: 255 g: 0 b: 0 }
     }
   }
 }
 
-# Draws annotations and overlays them on top of the original image coming into
-# the graph. Annotation drawing is performed on CPU, and the result is
-# transferred to GPU and overlaid on the input image. The calculator assumes
-# that image origin is always at the top-left corner and renders text
-# accordingly. However, the input image has its origin at the bottom-left corner
-# (OpenGL convention) and the flip_text_vertically option is set to true to
-# compensate that.
+# Draws annotations and overlays them on top of the input images.
 node {
   calculator: "AnnotationOverlayCalculator"
   input_stream: "INPUT_FRAME_GPU:throttled_input_video"
   input_stream: "render_data"
   output_stream: "OUTPUT_FRAME_GPU:output_video"
-  node_options: {
-    [type.googleapis.com/mediapipe.AnnotationOverlayCalculatorOptions] {
-      flip_text_vertically: true
-    }
-  }
 }

mediapipe/graphs/hair_segmentation/BUILD

@@ -1,4 +1,4 @@
-# Copyright 2019 The MediaPipeOSS Authors.
+# 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.
@@ -11,17 +11,16 @@
 # 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"])
 
 cc_library(
-    name = "android_calculators",
+    name = "mobile_calculators",
     deps = [
+        "//mediapipe/calculators/core:flow_limiter_calculator",
         "//mediapipe/calculators/core:previous_loopback_calculator",
-        "//mediapipe/calculators/core:real_time_flow_limiter_calculator",
         "//mediapipe/calculators/image:image_transformation_calculator",
         "//mediapipe/calculators/image:recolor_calculator",
         "//mediapipe/calculators/image:set_alpha_calculator",
@@ -29,6 +28,8 @@ cc_library(
         "//mediapipe/calculators/tflite:tflite_custom_op_resolver_calculator",
         "//mediapipe/calculators/tflite:tflite_inference_calculator",
         "//mediapipe/calculators/tflite:tflite_tensors_to_segmentation_calculator",
+        "//mediapipe/gpu:gpu_buffer_to_image_frame_calculator",
+        "//mediapipe/gpu:image_frame_to_gpu_buffer_calculator",
     ],
 )
 
@@ -38,16 +39,8 @@ load(
 )
 
 mediapipe_binary_graph(
-    name = "android_gpu_binary_graph",
-    graph = "hair_segmentation_android_gpu.pbtxt",
-    output_name = "android_gpu.binarypb",
-    deps = [
-        "//mediapipe/calculators/image:image_transformation_calculator_proto",
-        "//mediapipe/calculators/image:recolor_calculator_proto",
-        "//mediapipe/calculators/image:set_alpha_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_converter_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_custom_op_resolver_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_inference_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_tensors_to_segmentation_calculator_proto",
-    ],
+    name = "mobile_gpu_binary_graph",
+    graph = "hair_segmentation_mobile_gpu.pbtxt",
+    output_name = "mobile_gpu.binarypb",
+    deps = [":mobile_calculators"],
 )

mediapipe/graphs/hair_segmentation/hair_segmentation_mobile_gpu.pbtxt

@@ -20,7 +20,7 @@ output_stream: "output_video"
 # TfLiteConverterCalculator or TfLiteInferenceCalculator is still busy
 # processing previous inputs.
 node {
-  calculator: "RealTimeFlowLimiterCalculator"
+  calculator: "FlowLimiterCalculator"
   input_stream: "input_video"
   input_stream: "FINISHED:hair_mask"
   input_stream_info: {
@@ -47,14 +47,11 @@ node: {
   }
 }
 
-# Waits for a mask from the previous round of hair segmentation to be fed back
-# as an input, and caches it. Upon the arrival of an input image, it checks if
-# there is a mask cached, and sends out the mask with the timestamp replaced by
-# that of the input image. This is needed so that the "current image" and the
-# "previous mask" share the same timestamp, and as a result can be synchronized
-# and combined in the subsequent calculator. Note that upon the arrival of the
-# very first input frame, an empty packet is sent out to jump start the feedback
-# loop.
+# Caches a mask fed back from the previous round of hair segmentation, and upon
+# the arrival of the next input image sends out the cached mask with the
+# timestamp replaced by that of the input image, essentially generating a packet
+# that carries the previous mask. 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:throttled_input_video"
@@ -77,12 +74,9 @@ node {
 
 # Converts the transformed input image on GPU into an image tensor stored in
 # tflite::gpu::GlBuffer. The zero_center option is set to false to normalize the
-# pixel values to [0.f, 1.f] as opposed to [-1.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). With the max_num_channels option set to 4, all 4 RGBA
-# channels are contained in the image tensor.
+# pixel values to [0.f, 1.f] as opposed to [-1.f, 1.f]. With the
+# max_num_channels option set to 4, all 4 RGBA channels are contained in the
+# image tensor.
 node {
   calculator: "TfLiteConverterCalculator"
   input_stream: "IMAGE_GPU:mask_embedded_input_video"
@@ -90,7 +84,6 @@ node {
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteConverterCalculatorOptions] {
       zero_center: false
-      flip_vertically: true
       max_num_channels: 4
     }
   }

mediapipe/graphs/hand_tracking/BUILD

@@ -0,0 +1,113 @@
+# 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_binary_graph",
+    "mediapipe_simple_subgraph",
+)
+
+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",
+    ],
+)
+
+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_binary_graph(
+    name = "hand_tracking_mobile_gpu_binary_graph",
+    graph = "hand_tracking_mobile.pbtxt",
+    output_name = "hand_tracking_mobile_gpu.binarypb",
+    deps = [":mobile_calculators"],
+)
+
+cc_library(
+    name = "detection_mobile_calculators",
+    deps = [
+        ":hand_detection_gpu",
+        ":renderer_gpu",
+        "//mediapipe/calculators/core:flow_limiter_calculator",
+    ],
+)
+
+mediapipe_binary_graph(
+    name = "hand_detection_mobile_gpu_binary_graph",
+    graph = "hand_detection_mobile.pbtxt",
+    output_name = "hand_detection_mobile_gpu.binarypb",
+    deps = [":detection_mobile_calculators"],
+)

mediapipe/graphs/hand_tracking/hand_detection_gpu.pbtxt

@@ -0,0 +1,197 @@
+# 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 GPU 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_GPU:input_video"
+  output_stream: "IMAGE_GPU: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: "opresolver"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteCustomOpResolverCalculatorOptions] {
+      use_gpu: true
+    }
+  }
+}
+
+# Converts the transformed input image on GPU into an image tensor stored as a
+# TfLiteTensor.
+node {
+  calculator: "TfLiteConverterCalculator"
+  input_stream: "IMAGE_GPU:transformed_input_video"
+  output_stream: "TENSORS_GPU:image_tensor"
+}
+
+# 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_GPU:image_tensor"
+  output_stream: "TENSORS:detection_tensors"
+  input_side_packet: "CUSTOM_OP_RESOLVER:opresolver"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
+      model_path: "palm_detection.tflite"
+      use_gpu: true
+    }
+  }
+}
+
+# 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: 0.7
+    }
+  }
+}
+
+# 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 ("Palm"). 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: "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_GPU: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/hand_detection_mobile.pbtxt

@@ -0,0 +1,73 @@
+# MediaPipe graph that performs hand detection with TensorFlow Lite on GPU.
+# Used in the examples in
+# mediapipie/examples/android/src/java/com/mediapipe/apps/handdetectiongpu and
+# mediapipie/examples/ios/handdetectiongpu.
+
+# Images 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 HandDetectionSubgraph
+# downstream in the graph to finish its tasks before it passes through another
+# image. All images that come in while waiting are dropped, limiting the number
+# of in-flight images in HandDetectionSubgraph to 1. This prevents the nodes in
+# HandDetectionSubgraph 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., the
+# output produced by a node in the subgraph may get dropped downstream if the
+# subsequent nodes are still busy processing previous inputs.
+node {
+  calculator: "FlowLimiterCalculator"
+  input_stream: "input_video"
+  input_stream: "FINISHED:hand_rect_from_palm_detections"
+  input_stream_info: {
+    tag_index: "FINISHED"
+    back_edge: true
+  }
+  output_stream: "throttled_input_video"
+}
+
+# Subgraph that detections hands (see hand_detection_gpu.pbtxt).
+node {
+  calculator: "HandDetectionSubgraph"
+  input_stream: "throttled_input_video"
+  output_stream: "DETECTIONS:palm_detections"
+  output_stream: "NORM_RECT:hand_rect_from_palm_detections"
+}
+
+# Converts detections to drawing primitives for annotation overlay.
+node {
+  calculator: "DetectionsToRenderDataCalculator"
+  input_stream: "DETECTIONS:palm_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 normalized rects to drawing primitives for annotation overlay.
+node {
+  calculator: "RectToRenderDataCalculator"
+  input_stream: "NORM_RECT:hand_rect_from_palm_detections"
+  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_GPU:throttled_input_video"
+  input_stream: "detection_render_data"
+  input_stream: "rect_render_data"
+  output_stream: "OUTPUT_FRAME_GPU:output_video"
+}

mediapipe/graphs/hand_tracking/hand_landmark_gpu.pbtxt

@@ -0,0 +1,175 @@
+# 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_GPU:input_video"
+  input_stream: "NORM_RECT:hand_rect"
+  output_stream: "IMAGE_GPU:hand_image"
+}
+
+# Transforms the input image on GPU 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_GPU:hand_image"
+  output_stream: "IMAGE_GPU:transformed_hand_image"
+  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 as a
+# TfLiteTensor.
+node {
+  calculator: "TfLiteConverterCalculator"
+  input_stream: "IMAGE_GPU:transformed_hand_image"
+  output_stream: "TENSORS_GPU:image_tensor"
+}
+
+# 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_GPU:image_tensor"
+  output_stream: "TENSORS:output_tensors"
+  node_options: {
+    [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
+      model_path: "hand_landmark.tflite"
+      use_gpu: true
+    }
+  }
+}
+
+# Splits a vector of tensors into multiple vectors.
+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_GPU: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/hand_tracking_mobile.pbtxt

@@ -0,0 +1,123 @@
+# MediaPipe graph that performs hand tracking with TensorFlow Lite on GPU.
+# Used in the examples in
+# mediapipie/examples/android/src/java/com/mediapipe/apps/handtrackinggpu and
+# mediapipie/examples/ios/handtrackinggpu.
+
+# Images 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 downstream nodes
+# (calculators and subgraphs) in the graph to finish their tasks before it
+# passes through another image. All images that come in while waiting are
+# dropped, limiting the number of in-flight images in most part of the graph to
+# 1. This prevents the downstream nodes 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., the output produced by a node may get dropped downstream if the
+# subsequent nodes are still busy processing previous inputs.
+node {
+  calculator: "FlowLimiterCalculator"
+  input_stream: "input_video"
+  input_stream: "FINISHED:hand_rect"
+  input_stream_info: {
+    tag_index: "FINISHED"
+    back_edge: true
+  }
+  output_stream: "throttled_input_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:throttled_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: "throttled_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_gpu.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_gpu.pbtxt).
+node {
+  calculator: "HandLandmarkSubgraph"
+  input_stream: "IMAGE:throttled_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:throttled_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 formal 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_gpu.pbtxt).
+node {
+  calculator: "RendererSubgraph"
+  input_stream: "IMAGE:throttled_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/renderer_gpu.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_GPU:input_image"
+  input_stream: "detection_render_data"
+  input_stream: "landmark_render_data"
+  input_stream: "rect_render_data"
+  output_stream: "OUTPUT_FRAME_GPU:output_image"
+}

mediapipe/graphs/media_sequence/BUILD

@@ -1,4 +1,4 @@
-# Copyright 2019 The MediaPipeOSS Authors.
+# 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.
@@ -11,7 +11,6 @@
 # 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
 
@@ -29,3 +28,20 @@ cc_library(
         "//mediapipe/calculators/video:opencv_video_decoder_calculator",
     ],
 )
+
+cc_library(
+    name = "tvl1_flow_and_rgb_from_file_calculators",
+    deps = [
+        "//mediapipe/calculators/core:packet_inner_join_calculator",
+        "//mediapipe/calculators/core:packet_resampler_calculator",
+        "//mediapipe/calculators/core:sequence_shift_calculator",
+        "//mediapipe/calculators/image:opencv_image_encoder_calculator",
+        "//mediapipe/calculators/image:scale_image_calculator",
+        "//mediapipe/calculators/tensorflow:pack_media_sequence_calculator",
+        "//mediapipe/calculators/tensorflow:string_to_sequence_example_calculator",
+        "//mediapipe/calculators/tensorflow:unpack_media_sequence_calculator",
+        "//mediapipe/calculators/video:flow_to_image_calculator",
+        "//mediapipe/calculators/video:opencv_video_decoder_calculator",
+        "//mediapipe/calculators/video:tvl1_optical_flow_calculator",
+    ],
+)

mediapipe/graphs/media_sequence/clipped_images_from_file_at_24fps.pbtxt

@@ -1,4 +1,4 @@
-# Copyright 2019 The MediaPipeOSS Authors.
+# 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.
@@ -25,9 +25,9 @@ node {
   input_side_packet: "SEQUENCE_EXAMPLE:parsed_sequence_example"
   output_side_packet: "DATA_PATH:input_video_path"
   output_side_packet: "RESAMPLER_OPTIONS:packet_resampler_options"
-  options {
-    [mediapipe.UnpackMediaSequenceCalculatorOptions.ext]: {
-      base_packet_resampler_options {
+  node_options: {
+    [type.googleapis.com/mediapipe.UnpackMediaSequenceCalculatorOptions]: {
+      base_packet_resampler_options: {
         frame_rate: 24.0
         base_timestamp: 0
       }
@@ -55,7 +55,7 @@ node {
   calculator: "OpenCvImageEncoderCalculator"
   input_stream: "sampled_frames"
   output_stream: "encoded_frames"
-  node_options {
+  node_options: {
     [type.googleapis.com/mediapipe.OpenCvImageEncoderCalculatorOptions]: {
       quality: 80
     }

mediapipe/graphs/media_sequence/tvl1_flow_and_rgb_from_file.pbtxt

@@ -0,0 +1,153 @@
+# 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.
+
+# Convert the string input into a decoded SequenceExample.
+node {
+  calculator: "StringToSequenceExampleCalculator"
+  input_side_packet: "STRING:input_sequence_example"
+  output_side_packet: "SEQUENCE_EXAMPLE:parsed_sequence_example"
+}
+
+# Unpack the data path and clip timing from the SequenceExample.
+node {
+  calculator: "UnpackMediaSequenceCalculator"
+  input_side_packet: "SEQUENCE_EXAMPLE:parsed_sequence_example"
+  output_side_packet: "DATA_PATH:input_video_path"
+  output_side_packet: "RESAMPLER_OPTIONS:packet_resampler_options"
+  node_options: {
+    [type.googleapis.com/mediapipe.UnpackMediaSequenceCalculatorOptions]: {
+      base_packet_resampler_options: {
+        frame_rate: 25.0
+        base_timestamp: 0
+      }
+    }
+  }
+}
+
+# Decode the entire video.
+node {
+  calculator: "OpenCvVideoDecoderCalculator"
+  input_side_packet: "INPUT_FILE_PATH:input_video_path"
+  output_stream: "VIDEO:decoded_frames"
+}
+
+# Extract the subset of frames we want to keep.
+node {
+  calculator: "PacketResamplerCalculator"
+  input_stream: "decoded_frames"
+  output_stream: "sampled_frames"
+  input_side_packet: "OPTIONS:packet_resampler_options"
+}
+
+# Fit the images into the target size.
+node: {
+  calculator: "ScaleImageCalculator"
+  input_stream: "sampled_frames"
+  output_stream: "scaled_frames"
+  node_options: {
+    [type.googleapis.com/mediapipe.ScaleImageCalculatorOptions]: {
+      target_height: 256
+      preserve_aspect_ratio: true
+    }
+  }
+}
+
+# Shift the the timestamps of packets along a stream.
+# With a packet_offset of -1, the first packet will be dropped, the second will
+# be output with the timestamp of the first, the third with the timestamp of
+# the second, and so on.
+node: {
+  calculator: "SequenceShiftCalculator"
+  input_stream: "scaled_frames"
+  output_stream: "shifted_scaled_frames"
+  node_options: {
+    [type.googleapis.com/mediapipe.SequenceShiftCalculatorOptions]: {
+      packet_offset: -1
+    }
+  }
+}
+
+# Join the original input stream and the one that is shifted by one packet.
+node: {
+  calculator: "PacketInnerJoinCalculator"
+  input_stream: "scaled_frames"
+  input_stream: "shifted_scaled_frames"
+  output_stream: "first_frames"
+  output_stream: "second_frames"
+}
+
+# Compute the forward optical flow.
+node {
+  calculator: "Tvl1OpticalFlowCalculator"
+  input_stream: "FIRST_FRAME:first_frames"
+  input_stream: "SECOND_FRAME:second_frames"
+  output_stream: "FORWARD_FLOW:forward_flow"
+  max_in_flight: 32
+}
+
+# Convert an optical flow to be an image frame with 2 channels (v_x and v_y),
+# each channel is quantized to 0-255.
+node: {
+  calculator: "FlowToImageCalculator"
+  input_stream: "forward_flow"
+  output_stream: "flow_frames"
+  node_options: {
+    [type.googleapis.com/mediapipe.FlowToImageCalculatorOptions]: {
+      min_value: -20.0
+      max_value: 20.0
+    }
+  }
+}
+
+# Encode the optical flow images to store in the SequenceExample.
+node {
+  calculator: "OpenCvImageEncoderCalculator"
+  input_stream: "flow_frames"
+  output_stream: "encoded_flow_frames"
+  node_options: {
+    [type.googleapis.com/mediapipe.OpenCvImageEncoderCalculatorOptions]: {
+      quality: 100
+    }
+  }
+}
+
+# Encode the rgb images to store in the SequenceExample.
+node {
+  calculator: "OpenCvImageEncoderCalculator"
+  input_stream: "scaled_frames"
+  output_stream: "encoded_frames"
+  node_options: {
+    [type.googleapis.com/mediapipe.OpenCvImageEncoderCalculatorOptions]: {
+      quality: 100
+    }
+  }
+}
+
+# Store the images in the SequenceExample.
+node {
+  calculator: "PackMediaSequenceCalculator"
+  input_stream: "IMAGE:encoded_frames"
+  input_stream: "FORWARD_FLOW_ENCODED:encoded_flow_frames"
+  input_side_packet: "SEQUENCE_EXAMPLE:parsed_sequence_example"
+  output_side_packet: "SEQUENCE_EXAMPLE:sequence_example_to_serialize"
+}
+
+# Serialize the SequenceExample to a string for storage.
+node {
+  calculator: "StringToSequenceExampleCalculator"
+  input_side_packet: "SEQUENCE_EXAMPLE:sequence_example_to_serialize"
+  output_side_packet: "STRING:output_sequence_example"
+}
+
+num_threads: 32

mediapipe/graphs/object_detection/BUILD

@@ -1,4 +1,4 @@
-# Copyright 2019 The MediaPipeOSS Authors.
+# 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.
@@ -11,16 +11,15 @@
 # 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"])
 
 cc_library(
-    name = "android_calculators",
+    name = "mobile_calculators",
     deps = [
-        "//mediapipe/calculators/core:real_time_flow_limiter_calculator",
+        "//mediapipe/calculators/core:flow_limiter_calculator",
         "//mediapipe/calculators/image:image_transformation_calculator",
         "//mediapipe/calculators/tflite:ssd_anchors_calculator",
         "//mediapipe/calculators/tflite:tflite_converter_calculator",
@@ -77,35 +76,15 @@ load(
 )
 
 mediapipe_binary_graph(
-    name = "android_cpu_binary_graph",
-    graph = "object_detection_android_cpu.pbtxt",
-    output_name = "android_cpu.binarypb",
-    deps = [
-        "//mediapipe/calculators/image:image_transformation_calculator_proto",
-        "//mediapipe/calculators/tflite:ssd_anchors_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_converter_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_inference_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_tensors_to_detections_calculator_proto",
-        "//mediapipe/calculators/util:annotation_overlay_calculator_proto",
-        "//mediapipe/calculators/util:detection_label_id_to_text_calculator_proto",
-        "//mediapipe/calculators/util:detections_to_render_data_calculator_proto",
-        "//mediapipe/calculators/util:non_max_suppression_calculator_proto",
-    ],
+    name = "mobile_cpu_binary_graph",
+    graph = "object_detection_mobile_cpu.pbtxt",
+    output_name = "mobile_cpu.binarypb",
+    deps = [":mobile_calculators"],
 )
 
 mediapipe_binary_graph(
-    name = "android_gpu_binary_graph",
-    graph = "object_detection_android_gpu.pbtxt",
-    output_name = "android_gpu.binarypb",
-    deps = [
-        "//mediapipe/calculators/image:image_transformation_calculator_proto",
-        "//mediapipe/calculators/tflite:ssd_anchors_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_converter_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_inference_calculator_proto",
-        "//mediapipe/calculators/tflite:tflite_tensors_to_detections_calculator_proto",
-        "//mediapipe/calculators/util:annotation_overlay_calculator_proto",
-        "//mediapipe/calculators/util:detection_label_id_to_text_calculator_proto",
-        "//mediapipe/calculators/util:detections_to_render_data_calculator_proto",
-        "//mediapipe/calculators/util:non_max_suppression_calculator_proto",
-    ],
+    name = "mobile_gpu_binary_graph",
+    graph = "object_detection_mobile_gpu.pbtxt",
+    output_name = "mobile_gpu.binarypb",
+    deps = [":mobile_calculators"],
 )

mediapipe/graphs/object_detection/object_detection_desktop_tensorflow_graph.pbtxt

@@ -96,7 +96,7 @@ node {
 # Converts the detections to drawing primitives for annotation overlay.
 node {
   calculator: "DetectionsToRenderDataCalculator"
-  input_stream: "DETECTION_VECTOR:output_detections"
+  input_stream: "DETECTIONS:output_detections"
   output_stream: "RENDER_DATA:render_data"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
@@ -106,8 +106,7 @@ node {
   }
 }
 
-# Draws annotations and overlays them on top of the original image coming into
-# the graph.
+# Draws annotations and overlays them on top of the input images.
 node {
   calculator: "AnnotationOverlayCalculator"
   input_stream: "INPUT_FRAME:input_video"

mediapipe/graphs/object_detection/object_detection_desktop_tflite_graph.pbtxt

@@ -146,7 +146,7 @@ node {
 # Converts the detections to drawing primitives for annotation overlay.
 node {
   calculator: "DetectionsToRenderDataCalculator"
-  input_stream: "DETECTION_VECTOR:output_detections"
+  input_stream: "DETECTIONS:output_detections"
   output_stream: "RENDER_DATA:render_data"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
@@ -156,8 +156,7 @@ node {
   }
 }
 
-# Draws annotations and overlays them on top of the original image coming into
-# the graph.
+# Draws annotations and overlays them on top of the input images.
 node {
   calculator: "AnnotationOverlayCalculator"
   input_stream: "INPUT_FRAME:input_video"

mediapipe/graphs/object_detection/object_detection_mobile_cpu.pbtxt

@@ -1,6 +1,7 @@
 # MediaPipe graph that performs object detection with TensorFlow Lite on CPU.
-# Used in the example in
-# mediapipie/examples/android/src/java/com/mediapipe/apps/objectdetectioncpu.
+# Used in the examples in
+# mediapipie/examples/android/src/java/com/mediapipe/apps/objectdetectioncpu and
+# mediapipie/examples/ios/objectdetectioncpu.
 
 # Images on GPU coming into and out of the graph.
 input_stream: "input_video"
@@ -30,7 +31,7 @@ node: {
 # TfLiteConverterCalculator or TfLiteInferenceCalculator is still busy
 # processing previous inputs.
 node {
-  calculator: "RealTimeFlowLimiterCalculator"
+  calculator: "FlowLimiterCalculator"
   input_stream: "input_video_cpu"
   input_stream: "FINISHED:detections"
   input_stream_info: {
@@ -57,22 +58,12 @@ node: {
   }
 }
 
-# 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]. 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) and what
-# the model used in this graph is expecting (origin at the top-left corner).
+# 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"
-  node_options: {
-    [type.googleapis.com/mediapipe.TfLiteConverterCalculatorOptions] {
-      zero_center: true
-      flip_vertically: true
-    }
-  }
 }
 
 # Runs a TensorFlow Lite model on CPU that takes an image tensor and outputs a
@@ -139,7 +130,7 @@ node {
       y_scale: 10.0
       h_scale: 5.0
       w_scale: 5.0
-      flip_vertically: true
+      min_score_thresh: 0.6
     }
   }
 }
@@ -152,9 +143,9 @@ node {
   node_options: {
     [type.googleapis.com/mediapipe.NonMaxSuppressionCalculatorOptions] {
       min_suppression_threshold: 0.4
-      min_score_threshold: 0.6
       max_num_detections: 3
       overlap_type: INTERSECTION_OVER_UNION
+      return_empty_detections: true
     }
   }
 }
@@ -175,7 +166,7 @@ node {
 # Converts the detections to drawing primitives for annotation overlay.
 node {
   calculator: "DetectionsToRenderDataCalculator"
-  input_stream: "DETECTION_VECTOR:output_detections"
+  input_stream: "DETECTIONS:output_detections"
   output_stream: "RENDER_DATA:render_data"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
@@ -185,21 +176,12 @@ node {
   }
 }
 
-# Draws annotations and overlays them on top of the CPU copy of the original
-# image coming into the graph. The calculator assumes that image origin is
-# always at the top-left corner and renders text accordingly. However, the input
-# image has its origin at the bottom-left corner (OpenGL convention) and the
-# flip_text_vertically option is set to true to compensate that.
+# Draws annotations and overlays them on top of the input images.
 node {
   calculator: "AnnotationOverlayCalculator"
   input_stream: "INPUT_FRAME:throttled_input_video_cpu"
   input_stream: "render_data"
   output_stream: "OUTPUT_FRAME:output_video_cpu"
-  node_options: {
-    [type.googleapis.com/mediapipe.AnnotationOverlayCalculatorOptions] {
-      flip_text_vertically: true
-    }
-  }
 }
 
 # Transfers the annotated image from CPU back to GPU memory, to be sent out of

mediapipe/graphs/object_detection/object_detection_mobile_gpu.pbtxt

@@ -1,6 +1,7 @@
 # MediaPipe graph that performs object detection with TensorFlow Lite on GPU.
-# Used in the example in
-# mediapipie/examples/android/src/java/com/mediapipe/apps/objectdetectiongpu.
+# Used in the examples in
+# mediapipie/examples/android/src/java/com/mediapipe/apps/objectdetectiongpu and
+# mediapipie/examples/ios/objectdetectiongpu.
 
 # Images on GPU coming into and out of the graph.
 input_stream: "input_video"
@@ -20,7 +21,7 @@ output_stream: "output_video"
 # TfLiteConverterCalculator or TfLiteInferenceCalculator is still busy
 # processing previous inputs.
 node {
-  calculator: "RealTimeFlowLimiterCalculator"
+  calculator: "FlowLimiterCalculator"
   input_stream: "input_video"
   input_stream: "FINISHED:detections"
   input_stream_info: {
@@ -47,23 +48,12 @@ node: {
   }
 }
 
-# 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).
+# Converts the transformed input image on GPU into an image tensor stored as a
+# TfLiteTensor.
 node {
   calculator: "TfLiteConverterCalculator"
   input_stream: "IMAGE_GPU:transformed_input_video"
   output_stream: "TENSORS_GPU:image_tensor"
-  node_options: {
-    [type.googleapis.com/mediapipe.TfLiteConverterCalculatorOptions] {
-      zero_center: true
-      flip_vertically: true
-    }
-  }
 }
 
 # Runs a TensorFlow Lite model on GPU that takes an image tensor and outputs a
@@ -72,7 +62,7 @@ node {
 node {
   calculator: "TfLiteInferenceCalculator"
   input_stream: "TENSORS_GPU:image_tensor"
-  output_stream: "TENSORS_GPU:detection_tensors"
+  output_stream: "TENSORS:detection_tensors"
   node_options: {
     [type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions] {
       model_path: "ssdlite_object_detection.tflite"
@@ -115,7 +105,7 @@ node {
 # detections. Each detection describes a detected object.
 node {
   calculator: "TfLiteTensorsToDetectionsCalculator"
-  input_stream: "TENSORS_GPU:detection_tensors"
+  input_stream: "TENSORS:detection_tensors"
   input_side_packet: "ANCHORS:anchors"
   output_stream: "DETECTIONS:detections"
   node_options: {
@@ -130,7 +120,7 @@ node {
       y_scale: 10.0
       h_scale: 5.0
       w_scale: 5.0
-      flip_vertically: true
+      min_score_thresh: 0.6
     }
   }
 }
@@ -143,9 +133,9 @@ node {
   node_options: {
     [type.googleapis.com/mediapipe.NonMaxSuppressionCalculatorOptions] {
       min_suppression_threshold: 0.4
-      min_score_threshold: 0.6
       max_num_detections: 3
       overlap_type: INTERSECTION_OVER_UNION
+      return_empty_detections: true
     }
   }
 }
@@ -166,7 +156,7 @@ node {
 # Converts the detections to drawing primitives for annotation overlay.
 node {
   calculator: "DetectionsToRenderDataCalculator"
-  input_stream: "DETECTION_VECTOR:output_detections"
+  input_stream: "DETECTIONS:output_detections"
   output_stream: "RENDER_DATA:render_data"
   node_options: {
     [type.googleapis.com/mediapipe.DetectionsToRenderDataCalculatorOptions] {
@@ -176,21 +166,10 @@ node {
   }
 }
 
-# Draws annotations and overlays them on top of the original image coming into
-# the graph. Annotation drawing is performed on CPU, and the result is
-# transferred to GPU and overlaid on the input image. The calculator assumes
-# that image origin is always at the top-left corner and renders text
-# accordingly. However, the input image has its origin at the bottom-left corner
-# (OpenGL convention) and the flip_text_vertically option is set to true to
-# compensate that.
+# Draws annotations and overlays them on top of the input images.
 node {
   calculator: "AnnotationOverlayCalculator"
   input_stream: "INPUT_FRAME_GPU:throttled_input_video"
   input_stream: "render_data"
   output_stream: "OUTPUT_FRAME_GPU:output_video"
-  node_options: {
-    [type.googleapis.com/mediapipe.AnnotationOverlayCalculatorOptions] {
-      flip_text_vertically: true
-    }
-  }
 }