Skip to content

Commit 119ac00

Browse files
jaiveersinghNVjaiveersinghNV
authored
Merge pull request #18 from NVIDIA-ISAAC-ROS/release-dp3.1
Isaac ROS 0.31.0 (DP3.1)
2 parents 7c30f52 + 5dd56db commit 119ac00

File tree

4 files changed

+26
-24
lines changed

4 files changed

+26
-24
lines changed

‎README.md‎

Lines changed: 5 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -28,9 +28,9 @@ This package is powered by [NVIDIA Isaac Transport for ROS (NITROS)](https://dev
2828

2929
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.
3030

31-
| Sample Graph | Input Size | AGX Orin | Orin NX | Orin Nano 8GB | x86_64 w/ RTX 3060 Ti |
32-
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- |
33-
| [TensorRT Graph<br>PeopleSemSegNet](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_unet_graph.py) | 544p | [400 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_unet_graph-agx_orin.json)<br>5.5 ms | [218 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_unet_graph-orin_nx.json)<br>6.9 ms | [143 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_unet_graph-orin_nano_8gb.json)<br>12 ms | [1190 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_unet_graph-x86_64_rtx_3060Ti.json)<br>1.6 ms |
31+
| Sample Graph | Input Size | AGX Orin | Orin NX | Orin Nano 8GB | x86_64 w/ RTX 4060 Ti |
32+
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
33+
| [TensorRT Graph<br>PeopleSemSegNet](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_unet_graph.py) | 544p | [385 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_unet_graph-agx_orin.json)<br>6.9 ms | [210 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_unet_graph-orin_nx.json)<br>8.3 ms | [142 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_unet_graph-orin_nano.json)<br>13 ms | [827 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_unet_graph-nuc_4060ti.json)<br>4.0 ms |
3434

3535
## Table of Contents
3636

@@ -62,7 +62,7 @@ The following table summarizes the per-platform performance statistics of sample
6262

6363
## Latest Update
6464

65-
Update 2023-04-05: Source available GXF extensions
65+
Update 2023-05-25: Performance improvements.
6666

6767
## Supported Platforms
6868

@@ -292,6 +292,7 @@ For solutions to problems with using DNN models, please check [here](https://git
292292
293293
| Date | Changes |
294294
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
295+
| 2023-05-25 | Performance improvements |
295296
| 2023-04-05 | Source available GXF extensions |
296297
| 2022-10-19 | Updated OSS licensing |
297298
| 2022-08-31 | Update to be compatible with JetPack 5.0.2 |

‎isaac_ros_unet/config/unet_decoder_node.yaml‎

Lines changed: 17 additions & 16 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.
@@ -126,41 +126,37 @@ components:
126126
color_palette: []
127127
color_segmentation_mask_encoding: "rgb8"
128128
---
129-
name: raw_segmentation_mask_vault
129+
name: raw_segmentation_mask_sink
130130
components:
131131
- name: input_raw_segmentation_mask
132132
type: nvidia::gxf::DoubleBufferReceiver
133133
parameters:
134-
capacity: 1
134+
capacity: 2
135135
policy: 0
136136
- type: nvidia::gxf::MessageAvailableSchedulingTerm
137137
parameters:
138138
receiver: input_raw_segmentation_mask
139139
min_size: 1
140-
- name: vault
141-
type: nvidia::gxf::Vault
140+
- name: sink
141+
type: nvidia::isaac_ros::MessageRelay
142142
parameters:
143143
source: input_raw_segmentation_mask
144-
max_waiting_count: 1
145-
drop_waiting: false
146144
---
147-
name: colored_segmentation_mask_vault
145+
name: colored_segmentation_mask_sink
148146
components:
149147
- name: input_colored_segmentation_mask
150148
type: nvidia::gxf::DoubleBufferReceiver
151149
parameters:
152-
capacity: 1
150+
capacity: 2
153151
policy: 0
154152
- type: nvidia::gxf::MessageAvailableSchedulingTerm
155153
parameters:
156154
receiver: input_colored_segmentation_mask
157155
min_size: 1
158-
- name: vault
159-
type: nvidia::gxf::Vault
156+
- name: sink
157+
type: nvidia::isaac_ros::MessageRelay
160158
parameters:
161159
source: input_colored_segmentation_mask
162-
max_waiting_count: 1
163-
drop_waiting: false
164160
---
165161
components:
166162
- type: nvidia::gxf::Connection
@@ -170,20 +166,25 @@ components:
170166
- type: nvidia::gxf::Connection
171167
parameters:
172168
source: segmentation_broadcaster/output_raw_segmentation_mask
173-
target: raw_segmentation_mask_vault/input_raw_segmentation_mask
169+
target: raw_segmentation_mask_sink/input_raw_segmentation_mask
174170
- type: nvidia::gxf::Connection
175171
parameters:
176172
source: segmentation_broadcaster/output_video_buffer
177173
target: segmentation_mask_generator/input_video_buffer
178174
- type: nvidia::gxf::Connection
179175
parameters:
180176
source: segmentation_mask_generator/output_colored_segmentation_mask
181-
target: colored_segmentation_mask_vault/input_colored_segmentation_mask
177+
target: colored_segmentation_mask_sink/input_colored_segmentation_mask
182178
---
183179
components:
184180
- name: clock
185181
type: nvidia::gxf::RealtimeClock
186-
- type: nvidia::gxf::GreedyScheduler
182+
- type: nvidia::gxf::MultiThreadScheduler
187183
parameters:
188184
clock: clock
189185
stop_on_deadlock: false
186+
check_recession_period_ms: 1
187+
worker_thread_number: 2
188+
- type: nvidia::gxf::JobStatistics
189+
parameters:
190+
clock: clock

‎isaac_ros_unet/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_unet</name>
24-
<version>0.30.0</version>
24+
<version>0.31.0</version>
2525
<description>U-Net model processing</description>
2626

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

‎isaac_ros_unet/src/unet_decoder_node.cpp‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
// SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
2-
// Copyright (c) 2021-2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2+
// Copyright (c) 2021-2023 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.
@@ -43,11 +43,11 @@ constexpr char INPUT_COMPONENT_KEY[] = "segmentation_postprocessor/input_tensor"
4343
constexpr char INPUT_DEFAULT_TENSOR_FORMAT[] = "nitros_tensor_list_nhwc_rgb_f32";
4444
constexpr char INPUT_TOPIC_NAME[] = "tensor_sub";
4545

46-
constexpr char RAW_OUTPUT_COMPONENT_KEY[] = "raw_segmentation_mask_vault/vault";
46+
constexpr char RAW_OUTPUT_COMPONENT_KEY[] = "raw_segmentation_mask_sink/sink";
4747
constexpr char RAW_OUTPUT_DEFAULT_TENSOR_FORMAT[] = "nitros_image_mono8";
4848
constexpr char RAW_OUTPUT_TOPIC_NAME[] = "unet/raw_segmentation_mask";
4949

50-
constexpr char COLORED_OUTPUT_COMPONENT_KEY[] = "colored_segmentation_mask_vault/vault";
50+
constexpr char COLORED_OUTPUT_COMPONENT_KEY[] = "colored_segmentation_mask_sink/sink";
5151
constexpr char COLORED_OUTPUT_DEFAULT_TENSOR_FORMAT[] = "nitros_image_rgb8";
5252
constexpr char COLORED_OUTPUT_TOPIC_NAME[] = "unet/colored_segmentation_mask";
5353

0 commit comments

Comments
 (0)