Skip to content

Commit 9a11305

Browse files
jaiveersinghNVjaiveersinghNV
authored
Merge pull request #36 from NVIDIA-ISAAC-ROS/release-dp3.1
Isaac ROS 0.31.0 (DP3.1)
2 parents 1af625e + 68b5bf8 commit 9a11305

File tree

13 files changed

+65
-66
lines changed

13 files changed

+65
-66
lines changed

‎README.md‎

Lines changed: 9 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -40,13 +40,13 @@ This package is powered by [NVIDIA Isaac Transport for ROS (NITROS)](https://dev
4040

4141
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.
4242

43-
| Sample Graph | Input Size | AGX Orin | Orin NX | Orin Nano 8GB | x86_64 w/ RTX 3060 Ti |
44-
| ----------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |
45-
| [TensorRT Node<br>DOPE](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_tensor_rt_dope_node.py) | VGA | [48.1 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_dope_node-agx_orin.json)<br>22 ms | [17.2 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_dope_node-orin_nx.json)<br>56 ms | [13.0 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_dope_node-orin_nano_8gb.json)<br>79 ms | [94.9 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_dope_node-x86_64_rtx_3060Ti.json)<br>10 ms |
46-
| [Triton Node<br>DOPE](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_triton_dope_node.py) | VGA | [48.0 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_dope_node-agx_orin.json)<br>22 ms | [20.1 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_dope_node-orin_nx.json)<br>540 ms | [14.5 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_dope_node-orin_nano_8gb.json)<br>790 ms | [94.2 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_dope_node-x86_64_rtx_3060Ti.json)<br>11 ms |
47-
| [TensorRT Node<br>PeopleSemSegNet](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_tensor_rt_ps_node.py) | 544p | [467 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_ps_node-agx_orin.json)<br>2.3 ms | [270 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_ps_node-orin_nx.json)<br>4.0 ms | [184 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_ps_node-orin_nano_8gb.json)<br>9.0 ms | [1500 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_ps_node-x86_64_rtx_3060Ti.json)<br>1.1 ms |
48-
| [Triton Node<br>PeopleSemSegNet](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_triton_ps_node.py) | 544p | [293 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_ps_node-agx_orin.json)<br>3.7 ms | [191 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_ps_node-orin_nx.json)<br>5.5 ms | -- | [512 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_ps_node-x86_64_rtx_3060Ti.json)<br>2.1 ms |
49-
| [DNN Image Encoder Node](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_dnn_image_encoder_node.py) | VGA | [2230 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dnn_image_encoder_node-agx_orin.json)<br>0.60 ms | [1560 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dnn_image_encoder_node-orin_nx.json)<br>0.89 ms | -- | [5780 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dnn_image_encoder_node-x86_64_rtx_3060Ti.json)<br>0.45 ms |
43+
| Sample Graph | Input Size | AGX Orin | Orin NX | Orin Nano 8GB | x86_64 w/ RTX 4060 Ti |
44+
| ----------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
45+
| [TensorRT Node<br>DOPE](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_tensor_rt_dope_node.py) | VGA | [48.1 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_dope_node-agx_orin.json)<br>21 ms | [19.0 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_dope_node-orin_nx.json)<br>54 ms | [13.0 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_dope_node-orin_nano.json)<br>79 ms | [102 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_dope_node-nuc_4060ti.json)<br>10 ms |
46+
| [Triton Node<br>DOPE](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_triton_dope_node.py) | VGA | [48.0 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_dope_node-agx_orin.json)<br>22 ms | [20.5 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_dope_node-orin_nx.json)<br>540 ms | [14.5 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_dope_node-orin_nano.json)<br>790 ms | [99.4 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_dope_node-nuc_4060ti.json)<br>10 ms |
47+
| [TensorRT Node<br>PeopleSemSegNet](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_tensor_rt_ps_node.py) | 544p | [468 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_ps_node-agx_orin.json)<br>2.6 ms | [272 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_ps_node-orin_nx.json)<br>4.1 ms | [185 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_ps_node-orin_nano.json)<br>5.9 ms | [1990 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_tensor_rt_ps_node-nuc_4060ti.json)<br>0.88 ms |
48+
| [Triton Node<br>PeopleSemSegNet](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_triton_ps_node.py) | 544p | [296 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_ps_node-agx_orin.json)<br>3.5 ms | [190 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_ps_node-orin_nx.json)<br>5.5 ms | -- | [709 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_triton_ps_node-nuc_4060ti.json)<br>2.0 ms |
49+
| [DNN Image Encoder Node](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/scripts//isaac_ros_dnn_image_encoder_node.py) | VGA | [2120 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dnn_image_encoder_node-agx_orin.json)<br>1.1 ms | [1550 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dnn_image_encoder_node-orin_nx.json)<br>1.2 ms | -- | [5340 fps](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_benchmark/blob/main/results/isaac_ros_dnn_image_encoder_node-nuc_4060ti.json)<br>0.48 ms |
5050

5151
## Table of Contents
5252

@@ -87,7 +87,7 @@ The following table summarizes the per-platform performance statistics of sample
8787

8888
## Latest Update
8989

90-
Update 2023-04-05: Source available GXF extensions
90+
Update 2023-05-25: Performance improvements.
9191

9292
## Supported Platforms
9393

@@ -473,6 +473,7 @@ For solutions to problems with using DNN models, please check [here](docs/troubl
473473

474474
| Date | Changes |
475475
| ---------- | ---------------------------------------------------------------------------------------------------------------------------- |
476+
| 2023-05-25 | Performance improvements |
476477
| 2023-04-05 | Source available GXF extensions |
477478
| 2022-10-19 | Updated OSS licensing |
478479
| 2022-08-31 | Update to be compatible with JetPack 5.0.2 |

‎isaac_ros_dnn_encoders/config/dnn_image_encoder_node.yaml‎

Lines changed: 18 additions & 19 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.
@@ -19,36 +19,36 @@
1919
name: global
2020
components:
2121
- name: adapter_video_buffer
22-
type: nvidia::cvcore::tensor_ops::ImageAdapter
22+
type: nvidia::isaac::tensor_ops::ImageAdapter
2323
parameters:
2424
message_type: "VideoBuffer"
2525
- name: adapter_bgr_u8
26-
type: nvidia::cvcore::tensor_ops::ImageAdapter
26+
type: nvidia::isaac::tensor_ops::ImageAdapter
2727
parameters:
2828
message_type: "Tensor"
2929
image_type: "BGR_U8"
3030
- name: adapter_rgb_u8
31-
type: nvidia::cvcore::tensor_ops::ImageAdapter
31+
type: nvidia::isaac::tensor_ops::ImageAdapter
3232
parameters:
3333
message_type: "Tensor"
3434
image_type: "RGB_U8"
3535
- name: adapter_bgr_f32
36-
type: nvidia::cvcore::tensor_ops::ImageAdapter
36+
type: nvidia::isaac::tensor_ops::ImageAdapter
3737
parameters:
3838
message_type: "Tensor"
3939
image_type: "BGR_F32"
4040
- name: adapter_rgb_f32
41-
type: nvidia::cvcore::tensor_ops::ImageAdapter
41+
type: nvidia::isaac::tensor_ops::ImageAdapter
4242
parameters:
4343
message_type: "Tensor"
4444
image_type: "RGB_F32"
4545
- name: adapter_planar_bgr_f32
46-
type: nvidia::cvcore::tensor_ops::ImageAdapter
46+
type: nvidia::isaac::tensor_ops::ImageAdapter
4747
parameters:
4848
message_type: "Tensor"
4949
image_type: "PLANAR_BGR_F32"
5050
- name: adapter_planar_rgb_f32
51-
type: nvidia::cvcore::tensor_ops::ImageAdapter
51+
type: nvidia::isaac::tensor_ops::ImageAdapter
5252
parameters:
5353
message_type: "Tensor"
5454
image_type: "PLANAR_RGB_F32"
@@ -110,7 +110,7 @@ components:
110110
block_size: 1566720
111111
num_blocks: 40
112112
- name: resize_operator
113-
type: nvidia::cvcore::tensor_ops::Resize
113+
type: nvidia::isaac::tensor_ops::Resize
114114
parameters:
115115
output_width: 0
116116
output_height: 0
@@ -150,7 +150,7 @@ components:
150150
block_size: 1566720
151151
num_blocks: 40
152152
- name: color_converter_operator
153-
type: nvidia::cvcore::tensor_ops::ConvertColorFormat
153+
type: nvidia::isaac::tensor_ops::ConvertColorFormat
154154
parameters:
155155
output_type: "RGB_U8"
156156
receiver: data_receiver
@@ -186,7 +186,7 @@ components:
186186
block_size: 6266880
187187
num_blocks: 40
188188
- name: normalizer_operator
189-
type: nvidia::cvcore::tensor_ops::Normalize
189+
type: nvidia::isaac::tensor_ops::Normalize
190190
parameters:
191191
scales: [ 0.0156862745, 0.00490196078, 0.00784313725 ]
192192
offsets: [ -127.5, -153.0, -63.75 ]
@@ -223,7 +223,7 @@ components:
223223
block_size: 6266880
224224
num_blocks: 40
225225
- name: interleaved_to_planar_operator
226-
type: nvidia::cvcore::tensor_ops::InterleavedToPlanar
226+
type: nvidia::isaac::tensor_ops::InterleavedToPlanar
227227
parameters:
228228
receiver: data_receiver
229229
transmitter: data_transmitter
@@ -259,7 +259,7 @@ components:
259259
block_size: 6266880
260260
num_blocks: 40
261261
- name: reshape_operator
262-
type: nvidia::cvcore::tensor_ops::Reshape
262+
type: nvidia::isaac::tensor_ops::Reshape
263263
parameters:
264264
receiver: data_receiver
265265
transmitter: data_transmitter
@@ -304,7 +304,7 @@ components:
304304
camera_model_rx: data_receiver_timestamp
305305
tx: data_transmitter
306306
---
307-
name: vault
307+
name: sink
308308
components:
309309
- name: signal
310310
type: nvidia::gxf::DoubleBufferReceiver
@@ -315,12 +315,10 @@ components:
315315
parameters:
316316
receiver: signal
317317
min_size: 1
318-
- name: vault
319-
type: nvidia::gxf::Vault
318+
- name: sink
319+
type: nvidia::isaac_ros::MessageRelay
320320
parameters:
321321
source: signal
322-
max_waiting_count: 1
323-
drop_waiting: false
324322
---
325323
components:
326324
- name: edge0
@@ -376,12 +374,13 @@ components:
376374
type: nvidia::gxf::Connection
377375
parameters:
378376
source: compositor/data_transmitter
379-
target: vault/signal
377+
target: sink/signal
380378
---
381379
components:
382380
- type: nvidia::gxf::GreedyScheduler
383381
parameters:
384382
clock: clock
385383
stop_on_deadlock: false
384+
check_recession_period_us: 100
386385
- name: clock
387386
type: nvidia::gxf::RealtimeClock

‎isaac_ros_dnn_encoders/config/namespace_injector_rule.yaml‎

Lines changed: 6 additions & 6 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.
@@ -20,13 +20,13 @@ name: DNN Image Encoder Namespace Injector Rule
2020
operation: namespace_injector
2121
body:
2222
components:
23-
- type: nvidia::cvcore::tensor_ops::ConvertColorFormat
23+
- type: nvidia::isaac::tensor_ops::ConvertColorFormat
2424
path_parameter_keys: [input_adapter, output_adapter]
25-
- type: nvidia::cvcore::tensor_ops::Resize
25+
- type: nvidia::isaac::tensor_ops::Resize
2626
path_parameter_keys: [input_adapter, output_adapter]
27-
- type: nvidia::cvcore::tensor_ops::Normalize
27+
- type: nvidia::isaac::tensor_ops::Normalize
2828
path_parameter_keys: [input_adapter, output_adapter]
29-
- type: nvidia::cvcore::tensor_ops::InterleavedToPlanar
29+
- type: nvidia::isaac::tensor_ops::InterleavedToPlanar
3030
path_parameter_keys: [input_adapter, output_adapter]
31-
- type: nvidia::cvcore::tensor_ops::Reshape
31+
- type: nvidia::isaac::tensor_ops::Reshape
3232
path_parameter_keys: [input_adapter, output_adapter]

‎isaac_ros_dnn_encoders/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_dnn_encoders</name>
24-
<version>0.30.0</version>
24+
<version>0.31.0</version>
2525
<description>Encoders for preprocessing before running deep learning inference</description>
2626
<maintainer email="[email protected]">Hemal Shah</maintainer>
2727
<license>Apache-2.0</license>

0 commit comments

Comments
 (0)