Skip to content

Commit f4d2024

Browse files
LewisLiuPubLewisLiuPub
authored
Merge pull request #219 from pqLee/master
Dockerfile and bugfix.
2 parents f489fa0 + 6ba3844 commit f4d2024

File tree

9 files changed

+969
-0
lines changed

9 files changed

+969
-0
lines changed

‎doc/quick_start/getting_started_with_Dashing_Ubuntu18.04.md‎

Lines changed: 138 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,138 @@
1+
# ROS2_OpenVINO_Toolkit
2+
3+
**NOTE:**
4+
Below steps have been tested on **Ubuntu 18.04**.
5+
6+
## 1. Environment Setup
7+
* Install ROS2 Dashing [(guide)](https://docs.ros.org/en/dashing/Installation/Ubuntu-Install-Debians.html)
8+
* Install OpenVINO™ Toolkit Version: 2021.4 [(guide)](https://docs.openvino.ai/2021.4/openvino_docs_install_guides_installing_openvino_linux.html)
9+
* Install Intel® RealSense™ SDK (https://github.com/IntelRealSense/librealsense/blob/master/doc/distribution_linux.md).
10+
11+
## 2. Building and Installation
12+
* Install ROS2_OpenVINO packages
13+
```
14+
mkdir -p ~/catkin_ws/src
15+
cd ~/catkin_ws/src
16+
git clone https://github.com/intel/ros2_openvino_toolkit -b dashing
17+
git clone https://github.com/intel/ros2_object_msgs
18+
git clone https://github.com/IntelRealSense/realsense-ros.git -b ros2
19+
git clone https://github.com/ros-perception/vision_opencv -b ros2
20+
```
21+
* Install dependencies
22+
```
23+
sudo apt-get install ros-dashing-diagnostic-updater
24+
```
25+
* Build package
26+
```
27+
source /opt/ros/dashing/setup.bash
28+
source /opt/intel/openvino_2021/bin/setupvars.sh
29+
cd ~/catkin_ws
30+
colcon build --symlink-install
31+
source ./install/local_setup.bash
32+
```
33+
34+
## 3. Running the Demo
35+
* Preparation
36+
```
37+
source /opt/intel/openvino_2021/bin/setupvars.sh
38+
sudo mkdir -p /opt/openvino_toolkit
39+
sudo ln -s /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader /opt/openvino_toolkit/models
40+
sudo chmod 777 -R /opt/openvino_toolkit/models
41+
```
42+
43+
* See all available models
44+
```
45+
cd /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader
46+
sudo python3 downloader.py --print_all
47+
```
48+
49+
* Download the optimized Intermediate Representation (IR) of model (execute once)
50+
```
51+
cd /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader
52+
sudo python3 downloader.py --name face-detection-adas-0001 --output_dir /opt/openvino_toolkit/models/face_detection/output
53+
sudo python3 downloader.py --name age-gender-recognition-retail-0013 --output_dir /opt/openvino_toolkit/models/age-gender-recognition/output
54+
sudo python3 downloader.py --name emotions-recognition-retail-0003 --output_dir /opt/openvino_toolkit/models/emotions-recognition/output
55+
sudo python3 downloader.py --name head-pose-estimation-adas-0001 --output_dir /opt/openvino_toolkit/models/head-pose-estimation/output
56+
sudo python3 downloader.py --name person-detection-retail-0013 --output_dir /opt/openvino_toolkit/models/person-detection/output
57+
sudo python3 downloader.py --name person-reidentification-retail-0277 --output_dir /opt/openvino_toolkit/models/person-reidentification/output
58+
sudo python3 downloader.py --name landmarks-regression-retail-0009 --output_dir /opt/openvino_toolkit/models/landmarks-regression/output
59+
sudo python3 downloader.py --name semantic-segmentation-adas-0001 --output_dir /opt/openvino_toolkit/models/semantic-segmentation/output
60+
sudo python3 downloader.py --name vehicle-license-plate-detection-barrier-0106 --output_dir /opt/openvino_toolkit/models/vehicle-license-plate-detection/output
61+
sudo python3 downloader.py --name vehicle-attributes-recognition-barrier-0039 --output_dir /opt/openvino_toolkit/models/vehicle-attributes-recognition/output
62+
sudo python3 downloader.py --name license-plate-recognition-barrier-0001 --output_dir /opt/openvino_toolkit/models/license-plate-recognition/output
63+
sudo python3 downloader.py --name person-attributes-recognition-crossroad-0230 --output_dir /opt/openvino_toolkit/models/person-attributes/output
64+
```
65+
66+
* copy label files (execute once)
67+
* Before launch, copy label files to the same model path, make sure the model path and label path match the ros_openvino_toolkit/vino_launch/param/xxxx.yaml.
68+
```
69+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/face_detection/face-detection-adas-0001.labels /opt/openvino_toolkit/models/face_detection/output/intel/face-detection-adas-0001/FP32/
70+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/face_detection/face-detection-adas-0001.labels /opt/openvino_toolkit/models/face_detection/output/intel/face-detection-adas-0001/FP16/
71+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/emotions-recognition/FP32/emotions-recognition-retail-0003.labels /opt/openvino_toolkit/models/emotions-recognition/output/intel/emotions-recognition-retail-0003/FP32/
72+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/object_segmentation/frozen_inference_graph.labels /opt/openvino_toolkit/models/semantic-segmentation/output/FP32/
73+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/object_segmentation/frozen_inference_graph.labels /opt/openvino_toolkit/models/semantic-segmentation/output/FP16/
74+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/object_detection/vehicle-license-plate-detection-barrier-0106.labels /opt/openvino_toolkit/models/vehicle-license-plate-detection/output/intel/vehicle-license-plate-detection-barrier-0106/FP32
75+
```
76+
77+
* If the model (tensorflow, caffe, MXNet, ONNX, Kaldi)need to be converted to intermediate representation (For example the model for object detection)
78+
* ssd_mobilenet_v2_coco
79+
```
80+
cd /opt/openvino_toolkit/models/
81+
sudo python3 downloader/downloader.py --name ssd_mobilenet_v2_coco
82+
sudo python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/converter.py --name=ssd_mobilenet_v2_coco --mo /opt/intel/openvino_2021/deployment_tools/model_optimizer/mo.py
83+
```
84+
* deeplabv3
85+
```
86+
cd /opt/openvino_toolkit/models/
87+
sudo python3 downloader/downloader.py --name deeplabv3
88+
sudo python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/converter.py --name=deeplabv3 --mo /opt/intel/openvino_2021/deployment_tools/model_optimizer/mo.py
89+
```
90+
* YOLOV2
91+
```
92+
cd /opt/openvino_toolkit/models/
93+
sudo python3 downloader/downloader.py --name yolo-v2-tf
94+
sudo python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/converter.py --name=yolo-v2-tf --mo /opt/intel/openvino_2021/deployment_tools/model_optimizer/mo.py
95+
```
96+
97+
* Before launch, check the parameter configuration in ros2_openvino_toolkit/sample/param/xxxx.yaml, make sure the paramter like model path, label path, inputs are right.
98+
* run face detection sample code input from StandardCamera.
99+
```
100+
ros2 launch dynamic_vino_sample pipeline_people.launch.py
101+
```
102+
* run person reidentification sample code input from StandardCamera.
103+
```
104+
ros2 launch dynamic_vino_sample pipeline_reidentification.launch.py
105+
```
106+
* run person face reidentification sample code input from RealSenseCamera.
107+
```
108+
ros2 launch dynamic_vino_sample pipeline_face_reidentification.launch.py
109+
```
110+
* run face detection sample code input from Image.
111+
```
112+
ros2 launch dynamic_vino_sample pipeline_image.launch.py
113+
```
114+
* run object segmentation sample code input from RealSenseCamera.
115+
```
116+
ros2 launch dynamic_vino_sample pipeline_segmentation.launch.py
117+
```
118+
* run object segmentation sample code input from Image.
119+
```
120+
ros2 launch dynamic_vino_sample pipeline_segmentation_image.launch.py
121+
```
122+
* run vehicle detection sample code input from StandardCamera.
123+
```
124+
ros2 launch dynamic_vino_sample pipeline_vehicle_detection.launch.py
125+
```
126+
* run person attributes sample code input from StandardCamera.
127+
```
128+
ros2 launch dynamic_vino_sample pipeline_person_attributes.launch.py
129+
```
130+
131+
# More Information
132+
* ROS2 OpenVINO discription writen in Chinese: https://mp.weixin.qq.com/s/BgG3RGauv5pmHzV_hkVAdw
133+
134+
###### *Any security issue should be reported using process at https://01.org/security*
135+
136+
137+
138+

‎doc/quick_start/getting_started_with_Foxy_Ubuntu20.04.md‎

Lines changed: 136 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,136 @@
1+
# ROS2_FOXY_OpenVINO_Toolkit
2+
3+
**NOTE:**
4+
Below steps have been tested on **Ubuntu 20.04**.
5+
6+
## 1. Environment Setup
7+
* Install ROS2 Foxy ([guide](https://docs.ros.org/en/foxy/Installation/Ubuntu-Install-Debians.html))
8+
* Install Intel® OpenVINO™ Toolkit Version: 2021.4 ([guide]https://docs.openvino.ai/2021.4/openvino_docs_install_guides_installing_openvino_linux.html))
9+
* Install Intel® RealSense ™ SDK ([guide](https://github.com/IntelRealSense/librealsense/blob/master/doc/distribution_linux.md))
10+
11+
## 2. Building and Installation
12+
* Install ROS2_OpenVINO packages
13+
```
14+
mkdir -p ~/catkin_ws/src
15+
cd ~/catkin_ws/src
16+
git clone https://github.com/intel/ros2_openvino_toolkit -b foxy_dev
17+
git clone https://github.com/intel/ros2_object_msgs
18+
git clone https://github.com/IntelRealSense/realsense-ros.git -b ros2
19+
git clone https://github.com/ros-perception/vision_opencv.git -b ros2
20+
```
21+
* Install dependencies
22+
```
23+
sudo apt-get install ros-foxy-diagnostic-updater
24+
```
25+
* Build package
26+
```
27+
source /opt/ros/foxy/setup.bash
28+
source /opt/intel/openvino_2021/bin/setupvars.sh
29+
cd ~/catkin_ws
30+
colcon build --symlink-install
31+
source ./install/local_setup.bash
32+
```
33+
34+
## 3. Running the Demo
35+
* Preparation
36+
```
37+
source /opt/intel/openvino_2021/bin/setupvars.sh
38+
sudo mkdir -p /opt/openvino_toolkit
39+
sudo ln -s /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader /opt/openvino_toolkit/models
40+
sudo chmod 777 -R /opt/openvino_toolkit/models
41+
```
42+
43+
* See all available models
44+
```
45+
cd /opt/intel/<INSTALL_DIR>/deployment_tools/open_model_zoo/tools/downloader
46+
sudo python3 downloader.py --print_all
47+
```
48+
49+
* Download the optimized Intermediate Representation (IR) of model (execute once), for example:
50+
```
51+
cd /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader
52+
sudo python3 downloader.py --name face-detection-adas-0001 --output_dir /opt/openvino_toolkit/models/face_detection/output
53+
sudo python3 downloader.py --name age-gender-recognition-retail-0013 --output_dir /opt/openvino_toolkit/models/age-gender-recognition/output
54+
sudo python3 downloader.py --name emotions-recognition-retail-0003 --output_dir /opt/openvino_toolkit/models/emotions-recognition/output
55+
sudo python3 downloader.py --name head-pose-estimation-adas-0001 --output_dir /opt/openvino_toolkit/models/head-pose-estimation/output
56+
sudo python3 downloader.py --name person-detection-retail-0013 --output_dir /opt/openvino_toolkit/models/person-detection/output
57+
sudo python3 downloader.py --name person-reidentification-retail-0277 --output_dir /opt/openvino_toolkit/models/person-reidentification/output
58+
sudo python3 downloader.py --name landmarks-regression-retail-0009 --output_dir /opt/openvino_toolkit/models/landmarks-regression/output
59+
sudo python3 downloader.py --name semantic-segmentation-adas-0001 --output_dir /opt/openvino_toolkit/models/semantic-segmentation/output
60+
sudo python3 downloader.py --name vehicle-license-plate-detection-barrier-0106 --output_dir /opt/openvino_toolkit/models/vehicle-license-plate-detection/output
61+
sudo python3 downloader.py --name vehicle-attributes-recognition-barrier-0039 --output_dir /opt/openvino_toolkit/models/vehicle-attributes-recognition/output
62+
sudo python3 downloader.py --name license-plate-recognition-barrier-0001 --output_dir /opt/openvino_toolkit/models/license-plate-recognition/output
63+
sudo python3 downloader.py --name person-attributes-recognition-crossroad-0230 --output_dir /opt/openvino_toolkit/models/person-attributes/output
64+
```
65+
66+
* copy label files (execute once)
67+
* Before launch, copy label files to the same model path, make sure the model path and label path match the ros_openvino_toolkit/vino_launch/param/xxxx.yaml.
68+
```
69+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/face_detection/face-detection-adas-0001.labels /opt/openvino_toolkit/models/face_detection/output/intel/face-detection-adas-0001/FP32/
70+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/face_detection/face-detection-adas-0001.labels /opt/openvino_toolkit/models/face_detection/output/intel/face-detection-adas-0001/FP16/
71+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/emotions-recognition/FP32/emotions-recognition-retail-0003.labels /opt/openvino_toolkit/models/emotions-recognition/output/intel/emotions-recognition-retail-0003/FP32/
72+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/object_segmentation/frozen_inference_graph.labels /opt/openvino_toolkit/models/semantic-segmentation/output/FP32/
73+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/object_segmentation/frozen_inference_graph.labels /opt/openvino_toolkit/models/semantic-segmentation/output/FP16/
74+
sudo cp ~/catkin_ws/src/ros2_openvino_toolkit/data/labels/object_detection/vehicle-license-plate-detection-barrier-0106.labels /opt/openvino_toolkit/models/vehicle-license-plate-detection/output/intel/vehicle-license-plate-detection-barrier-0106/FP32
75+
```
76+
77+
* If the model (tensorflow, caffe, MXNet, ONNX, Kaldi)need to be converted to intermediate representation (For example the model for object detection)
78+
* (Note: Tensorflow=1.15.5, Python<=3.7)
79+
* ssd_mobilenet_v2_coco
80+
```
81+
cd /opt/openvino_toolkit/models/
82+
sudo python3 downloader/downloader.py --name ssd_mobilenet_v2_coco
83+
sudo python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/converter.py --name=ssd_mobilenet_v2_coco --mo /opt/intel/openvino_2021/deployment_tools/model_optimizer/mo.py
84+
```
85+
* deeplabv3
86+
```
87+
cd /opt/openvino_toolkit/models/
88+
sudo python3 downloader/downloader.py --name deeplabv3
89+
sudo python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/converter.py --name=deeplabv3 --mo /opt/intel/openvino_2021/deployment_tools/model_optimizer/mo.py
90+
```
91+
* YOLOV2
92+
```
93+
cd /opt/openvino_toolkit/models/
94+
sudo python3 downloader/downloader.py --name yolo-v2-tf
95+
sudo python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/converter.py --name=yolo-v2-tf --mo /opt/intel/openvino_2021/deployment_tools/model_optimizer/mo.py
96+
```
97+
98+
* Before launch, check the parameter configuration in ros2_openvino_toolkit/sample/param/xxxx.yaml, make sure the paramter like model path, label path, inputs are right.
99+
* run face detection sample code input from StandardCamera.
100+
```
101+
ros2 launch dynamic_vino_sample pipeline_people.launch.py
102+
```
103+
* run person reidentification sample code input from StandardCamera.
104+
```
105+
ros2 launch dynamic_vino_sample pipeline_reidentification.launch.py
106+
```
107+
* run person face reidentification sample code input from RealSenseCamera.
108+
```
109+
ros2 launch dynamic_vino_sample pipeline_face_reidentification.launch.py
110+
```
111+
* run face detection sample code input from Image.
112+
```
113+
ros2 launch dynamic_vino_sample pipeline_image.launch.py
114+
```
115+
* run object segmentation sample code input from RealSenseCameraTopic.
116+
```
117+
ros2 launch dynamic_vino_sample pipeline_segmentation.launch.py
118+
```
119+
* run object segmentation sample code input from Image.
120+
```
121+
ros2 launch dynamic_vino_sample pipeline_segmentation_image.launch.py
122+
```
123+
* run vehicle detection sample code input from StandardCamera.
124+
```
125+
ros2 launch dynamic_vino_sample pipeline_vehicle_detection.launch.py
126+
```
127+
* run person attributes sample code input from StandardCamera.
128+
```
129+
ros2 launch dynamic_vino_sample pipeline_person_attributes.launch.py
130+
```
131+
132+
# More Information
133+
* ROS2 OpenVINO discription writen in Chinese: https://mp.weixin.qq.com/s/BgG3RGauv5pmHzV_hkVAdw
134+
135+
###### *Any security issue should be reported using process at https://01.org/security*
136+

0 commit comments

Comments
 (0)