Skip to content

Commit ae1368a

Browse files
jaiveersinghNVjaiveersinghNV
committed
Isaac ROS 0.31.0 (DP3.1)
1 parent 3d30a38 commit ae1368a

File tree

4 files changed

+23
-20
lines changed

4 files changed

+23
-20
lines changed

‎README.md‎

Lines changed: 9 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -20,10 +20,10 @@ This package is powered by [NVIDIA Isaac Transport for ROS (NITROS)](https://dev
2020

2121
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.
2222

23-
| Sample Graph | Input Size | AGX Orin | Orin NX | Orin Nano 8GB | x86_64 w/ RTX 3060 Ti |
24-
| --------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | -------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
25-
| [Freespace Segmentation Node](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_bi3d_fs_node.py) | 576p | [1680 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-agx_orin.json)<br>1.1 ms | [1240 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-orin_nx.json)<br>1.3 ms | [926 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-orin_nano_8gb.json)<br>1.7 ms | [2830 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-x86_64_rtx_3060Ti.json)<br>0.31 ms |
26-
| [Freespace Segmentation Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_bi3d_fs_graph.py) | 576p | [53.7 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-agx_orin.json)<br>41 ms | [28.1 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-orin_nx.json)<br>120 ms | [19.4 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-orin_nano_8gb.json)<br>100 ms | [167 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-x86_64_rtx_3060Ti.json)<br>26 ms |
23+
| Sample Graph | Input Size | AGX Orin | Orin NX | Orin Nano 8GB | x86_64 w/ RTX 4060 Ti |
24+
| --------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | -------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
25+
| [Freespace Segmentation Node](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_bi3d_fs_node.py) | 576p | [1800 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-agx_orin.json)<br>1.5 ms | [1710 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-orin_nx.json)<br>1.8 ms | [1140 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-orin_nano.json)<br>2.1 ms | [3500 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_node-nuc_4060ti.json)<br>0.36 ms |
26+
| [Freespace Segmentation Graph](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_bi3d_fs_graph.py) | 576p | [54.0 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-agx_orin.json)<br>36 ms | [28.4 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-orin_nx.json)<br>120 ms | [23.6 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-orin_nano.json)<br>140 ms | [178 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_bi3d_fs_graph-nuc_4060ti.json)<br>30 ms |
2727

2828

2929
## Table of Contents
@@ -52,7 +52,7 @@ The following table summarizes the per-platform performance statistics of sample
5252

5353
## Latest Update
5454

55-
Update 2023-04-05: Initial release
55+
Update 2023-05-25: Performance improvements.
5656

5757
## Supported Platforms
5858

@@ -248,6 +248,7 @@ Check [here](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_dnn_inference/blob/ma
248248

249249
## Updates
250250

251-
| Date | Changes |
252-
| ---------- | --------------- |
253-
| 2023-04-05 | Initial release |
251+
| Date | Changes |
252+
| ---------- | ------------------------ |
253+
| 2023-05-25 | Performance improvements |
254+
| 2023-04-05 | Initial release |

‎isaac_ros_bi3d_freespace/config/freespace_segmentation_node.yaml‎

Lines changed: 11 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
%YAML 1.2
22
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
3-
# Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
3+
# Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
44
#
55
# Licensed under the Apache License, Version 2.0 (the "License");
66
# you may not use this file except in compliance with the License.
@@ -50,7 +50,7 @@ components:
5050
transmitter: occupancy_grid_out
5151
min_size: 1
5252
---
53-
name: vault
53+
name: sink
5454
components:
5555
- name: signal
5656
type: nvidia::gxf::DoubleBufferReceiver
@@ -61,24 +61,26 @@ components:
6161
parameters:
6262
receiver: signal
6363
min_size: 1
64-
- name: vault
65-
type: nvidia::gxf::Vault
64+
- name: sink
65+
type: nvidia::isaac_ros::MessageRelay
6666
parameters:
6767
source: signal
68-
max_waiting_count: 1
69-
drop_waiting: false
7068
---
7169
components:
7270
- name: edge0
7371
type: nvidia::gxf::Connection
7472
parameters:
7573
source: freespace_segmentation/occupancy_grid_out
76-
target: vault/signal
74+
target: sink/signal
7775
---
7876
components:
77+
- name: clock
78+
type: nvidia::gxf::RealtimeClock
7979
- type: nvidia::gxf::GreedyScheduler
8080
parameters:
8181
clock: clock
8282
stop_on_deadlock: false
83-
- name: clock
84-
type: nvidia::gxf::RealtimeClock
83+
check_recession_period_us: 100
84+
- type: nvidia::gxf::JobStatistics
85+
parameters:
86+
clock: clock

‎isaac_ros_bi3d_freespace/package.xml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,7 @@ SPDX-License-Identifier: Apache-2.0
2121
<?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
2222
<package format="3">
2323
<name>isaac_ros_bi3d_freespace</name>
24-
<version>0.30.0</version>
24+
<version>0.31.0</version>
2525
<description>Freespace segmentation using the Bi3D inference network for ROS</description>
2626

2727
<maintainer email="[email protected]">Hemal Shah</maintainer>

‎isaac_ros_bi3d_freespace/src/freespace_segmentation_node.cpp‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
// SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
2-
// Copyright (c) 2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2+
// Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
33
//
44
// Licensed under the Apache License, Version 2.0 (the "License");
55
// you may not use this file except in compliance with the License.
@@ -37,7 +37,7 @@ constexpr char INPUT_COMPONENT_KEY[] = "freespace_segmentation/mask_in";
3737
constexpr char INPUT_DEFAULT_TENSOR_FORMAT[] = "nitros_disparity_image_32FC1";
3838
constexpr char INPUT_TOPIC_NAME[] = "bi3d_mask";
3939

40-
constexpr char OUTPUT_COMPONENT_KEY[] = "vault/vault";
40+
constexpr char OUTPUT_COMPONENT_KEY[] = "sink/sink";
4141
constexpr char OUTPUT_DEFAULT_TENSOR_FORMAT[] = "nitros_occupancy_grid";
4242
constexpr char OUTPUT_TOPIC_NAME[] = "freespace_segmentation/occupancy_grid";
4343

0 commit comments

Comments
 (0)