Merge pull request #19 from NVIDIA-ISAAC-ROS/release-dp3.1

Isaac ROS 0.31.0 (DP3.1)

Author: hemalshahNV

README.md

@@ -22,11 +22,10 @@ Packages in this repository rely on accelerated DNN model inference using [Trito
 
 The following table summarizes the per-platform performance statistics of sample graphs that use this package, with links included to the full benchmark output. These benchmark configurations are taken from the [Isaac ROS Benchmark](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark#list-of-isaac-ros-benchmarks) collection, based on the [`ros2_benchmark`](https://github.com/NVIDIA-ISAAC-ROS/ros2_benchmark) framework.
 
-| Sample Graph                                                                                                                                         | Input Size | AGX Orin                                                                                                                                        | Orin NX                                                                                                                                        | Orin Nano 8GB                                                                                                                                        | x86_64 w/ RTX 3060 Ti                                                                                                                                    |
-| ---------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| [DOPE Pose Estimation Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_dope_graph.py)             | VGA        | [40.4 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dope_graph-agx_orin.json)<br>29 ms       | [16.7 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dope_graph-orin_nx.json)<br>120 ms      | --                                                                                                                                                   | [82.8 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dope_graph-x86_64_rtx_3060Ti.json)<br>14 ms       |
-| [Centerpose Pose Estimation Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_centerpose_graph.py) | VGA        | [50.2 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_centerpose_graph-agx_orin.json)<br>38 ms | [20.2 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_centerpose_graph-orin_nx.json)<br>67 ms | [15.2 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_centerpose_graph-orin_nano_8gb.json)<br>85 ms | [13.5 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_centerpose_graph-x86_64_rtx_3060Ti.json)<br>42 ms |
-
+| Sample Graph                                                                                                                                         | Input Size | AGX Orin                                                                                                                                        | Orin NX                                                                                                                                        | Orin Nano 8GB                                                                                                                                         | x86_64 w/ RTX 4060 Ti                                                                                                                             |
+| ---------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [DOPE Pose Estimation Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_dope_graph.py)             | VGA        | [40.5 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dope_graph-agx_orin.json)<br>31 ms       | [17.6 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dope_graph-orin_nx.json)<br>120 ms      | --                                                                                                                                                    | [90.9 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dope_graph-nuc_4060ti.json)<br>14 ms       |
+| [Centerpose Pose Estimation Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_centerpose_graph.py) | VGA        | [50.2 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_centerpose_graph-agx_orin.json)<br>37 ms | [23.7 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_centerpose_graph-orin_nx.json)<br>70 ms | [18.4 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_centerpose_graph-orin_nano_emul.json)<br>87 ms | [45.0 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_centerpose_graph-nuc_4060ti.json)<br>21 ms |
 
 ## Table of Contents
 
@@ -63,7 +62,7 @@ The following table summarizes the per-platform performance statistics of sample
 
 ## Latest Update
 
-Update 2023-04-05: Source available GXF extensions
+Update 2023-05-25: Performance improvements.
 
 ## Supported Platforms
 
@@ -371,6 +370,7 @@ For solutions to problems with using DNN models, please check [here](https://git
 
 | Date       | Changes                                                                                                  |
 | ---------- | -------------------------------------------------------------------------------------------------------- |
+| 2023-05-25 | Performance improvements                                                                                 |
 | 2023-04-05 | Source available GXF extensions                                                                          |
 | 2022-06-30 | Update to use NITROS for improved performance and to be compatible with JetPack 5.0.2                    |
 | 2022-06-30 | Refactored README, updated launch file & added `nvidia` namespace, dropped Jetson support for CenterPose |

isaac_ros_centerpose/package.xml

@@ -21,7 +21,7 @@
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>isaac_ros_centerpose</name>
-  <version>0.30.0</version>
+  <version>0.31.0</version>
   <description>CenterPose: Pose Estimation using Deep Learning</description>
 
   <maintainer email="[email protected]">Hemal Shah</maintainer>

isaac_ros_centerpose/setup.py

@@ -24,7 +24,7 @@
 
 setup(
     name=package_name,
-    version='0.30.0',
+    version='0.31.0',
     packages=[package_name],
     data_files=[
         ('share/ament_index/resource_index/packages',

isaac_ros_dope/config/dope_node.yaml

@@ -1,6 +1,6 @@
 %YAML 1.2
 # SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
-# Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -48,35 +48,38 @@ components:
     transmitter: posearray_out
     min_size: 1
 ---
-name: vault
+name: sink
 components:
 - name: signal
   type: nvidia::gxf::DoubleBufferReceiver
   parameters:
-    capacity: 1
+    capacity: 2
     policy: 0
 - type: nvidia::gxf::MessageAvailableSchedulingTerm
   parameters:
     receiver: signal
     min_size: 1
-- name: vault
-  type: nvidia::gxf::Vault
+- name: sink
+  type: nvidia::isaac_ros::MessageRelay
   parameters:
     source: signal
-    max_waiting_count: 1
-    drop_waiting: false
 ---
 components:
 - name: edge0
   type: nvidia::gxf::Connection
   parameters:
     source: dope_decoder/posearray_out
-    target: vault/signal
+    target: sink/signal
 ---
 components:
-- type: nvidia::gxf::GreedyScheduler
+- name: clock
+  type: nvidia::gxf::RealtimeClock
+- type: nvidia::gxf::MultiThreadScheduler
   parameters:
     clock: clock
     stop_on_deadlock: false
-- name: clock
-  type: nvidia::gxf::RealtimeClock
+    check_recession_period_ms: 1
+    worker_thread_number: 2
+- type: nvidia::gxf::JobStatistics
+  parameters:
+    clock: clock

isaac_ros_dope/package.xml

@@ -21,7 +21,7 @@
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>isaac_ros_dope</name>
-  <version>0.30.0</version>
+  <version>0.31.0</version>
   <description>Deep learning based pose estimation</description>
 
   <maintainer email="[email protected]">Jaiveer Singh</maintainer>

isaac_ros_dope/src/dope_decoder_node.cpp

@@ -1,5 +1,5 @@
 // SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
-// Copyright (c) 2021-2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+// Copyright (c) 2021-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -45,7 +45,7 @@ constexpr char INPUT_COMPONENT_KEY[] = "dope_decoder/tensorlist_in";
 constexpr char INPUT_DEFAULT_TENSOR_FORMAT[] = "nitros_tensor_list_nchw_rgb_f32";
 constexpr char INPUT_TOPIC_NAME[] = "belief_map_array";
 
-constexpr char OUTPUT_COMPONENT_KEY[] = "vault/vault";
+constexpr char OUTPUT_COMPONENT_KEY[] = "sink/sink";
 constexpr char OUTPUT_DEFAULT_TENSOR_FORMAT[] = "nitros_pose_array";
 constexpr char OUTPUT_TOPIC_NAME[] = "dope/pose_array";