Conversation
…ject_detection_ssd model
| # This file can be used with the --list option of the model downloader. | ||
| face-detection-adas-0001 | ||
| age-gender-recognition-retail-0013 | ||
| emotions-recognition-retail-0003 |
There was a problem hiding this comment.
no found the xml: face-reidentification-retail-0095.xml
if it is need.
There was a problem hiding this comment.
and the xml vehicle-license-plate-detection-barrier-0123.xml
| && rm -rf /var/lib/apt/lists/* | ||
|
|
||
| # other dependencies | ||
| RUN apt-get update && apt-get install -y python3-pip && python3 -m pip install -U \ |
| * Before launch, check the parameter configuration in ros_openvino_toolkit/sample/param/xxxx.yaml, make sure the paramter like model path, label path, inputs are right. | ||
| * run face detection sample code input from StandardCamera. | ||
| ``` | ||
| roslaunch vino_launch pipeline_people.launch |
There was a problem hiding this comment.
According the ducument the path such as xml image and labels etc in the yaml file that need your adjustment like ros2_openvino_toolkit.
| sudo cp ~/catkin_ws/src/ros_openvino_toolkit/data/labels/emotions-recognition/FP32/emotions-recognition-retail-0003.labels /opt/openvino_toolkit/models/emotions-recognition/output/intel/emotions-recognition-retail-0003/FP16/ | ||
| sudo cp ~/catkin_ws/src/ros_openvino_toolkit/data/labels/face_detection/face-detection-adas-0001.labels /opt/openvino_toolkit/models/face_detection/output/intel/face-detection-adas-0001/FP32/ | ||
| sudo cp ~/catkin_ws/src/ros_openvino_toolkit/data/labels/face_detection/face-detection-adas-0001.labels /opt/openvino_toolkit/models/face_detection/output/intel/face-detection-adas-0001/FP16/ | ||
| sudo cp ~/catkin_ws/src/ros_openvino_toolkit/data/labels/object_detection/vehicle-license-plate-detection-barrier-0106.labels /opt/openvino_toolkit/models/vehicle-license-plate-detection/output/convert/intel/vehicle-license-plate-detection-barrier-0106/FP32 |
There was a problem hiding this comment.
There is used FP16/vehicle-license-plate-detection-barrier-0106.labels at the pipeline_vehicle_detection.yaml. but there are FP32
| } | ||
|
|
||
| virtual bool updateLayerProperty(const InferenceEngine::CNNNetwork&) | ||
| virtual bool updateLayerProperty(std::shared_ptr<ov::Model>&) |
.vscode/settings.json
Outdated
| "variant": "cpp", | ||
| "bit": "cpp" | ||
| } | ||
| } No newline at end of file |
data/model_list/download_model.lst
Outdated
| semantic-segmentation-adas-0001 | ||
| mobilenet-ssd | ||
| deeplabv3 | ||
| face-reidentification-retail-0095.xml |
There was a problem hiding this comment.
sorry, it should be
face-reidentification-retail-0095 and
vehicle-license-plate-detection-barrier-0123.
LewisLiuPub
left a comment
There was a problem hiding this comment.
Please evaluate my comments and sync them with ROS2 version.
docker/Dockerfile
Outdated
| # ENV FTP_PROXY="your_proxy" | ||
|
|
||
| # maintainer information | ||
| LABEL maintainer="Jiawei Wu <jiawei.wu@intel.com>" |
There was a problem hiding this comment.
It's better to label the author info: LABEL author="Jiawei Wu jiawei.wu@intel.com"
docker/Dockerfile
Outdated
| @@ -0,0 +1,82 @@ | |||
| # ros openvino toolkit env master ec5b9b9716e4 | |||
|
|
|||
| ARG ROS_VERSION | |||
There was a problem hiding this comment.
rename ROS_VERSION -->ROS_PRE_INSTALLED_PKG?
|
|
||
| ARG ROS_VERSION | ||
| FROM osrf/ros:${ROS_VERSION} | ||
| ARG VERSION |
There was a problem hiding this comment.
update these 3 lines above as:
ARG VERSION=noetic
ARG ROS_PRE_INSTALLED_PKG=${VERSION}-desktop-full
FROM osrf/ros:${ROS_PRE_INSTALLED_PKG}
docker/docker_instruction.md
Outdated
| ``` | ||
| cd ~/ros_openvino_toolkit/docker/Dockerfile | ||
| vi ~/ros_openvino_toolkit/docker/Dockerfile | ||
| docker build --build-arg ROS_VERSION=<EXPECT_ROS_BASE_IMAGE> --build-arg VERSION=<EXPECT_ROS_VERSION> --build-arg "HTTP_PROXY=set_your_proxy" -t ros_openvino_202201 . |
There was a problem hiding this comment.
- ROS_VERSION and VERSION, quite similar, rename it.
- what if we always install xxxx-desktop-full? making ROS_VERSION optional in the command.
docker/Dockerfile
Outdated
| WORKDIR /root/catkin_ws/src | ||
| RUN git init && git clone -b ros https://github.com/intel/ros_openvino_toolkit \ | ||
| && git clone https://github.com/intel/object_msgs.git \ | ||
| && git clone -b ${VERSION} https://github.com/ros-perception/vision_opencv.git \ |
There was a problem hiding this comment.
cv_bridge and realsense-ros should be install by "apt install xxxx"
docker/Dockerfile
Outdated
| requests \ | ||
| && apt-get install -y --no-install-recommends libboost-all-dev | ||
| WORKDIR /usr/lib/x86_64-linux-gnu | ||
| RUN ln -sf libboost_python-py36.so libboost_python37.so |
There was a problem hiding this comment.
Don't link between different versions.
We should find the root cause, then find the true implementation.
| && git clone https://github.com/intel/object_msgs.git \ | ||
| && git clone -b ${VERSION} https://github.com/ros-perception/vision_opencv.git \ | ||
| && git clone -b ros1-legacy https://github.com/IntelRealSense/realsense-ros.git | ||
| && git clone https://github.com/intel/object_msgs.git |
There was a problem hiding this comment.
why remove the git of vision_opencv and realsense?
There was a problem hiding this comment.
No dependency on this two package.
| input_path: to/be/set/video_path | ||
| infers: | ||
| - name: ObjectDetection | ||
| model: /opt/openvino_toolkit/models/public/vehicle-license-plate-detection-barrier-0123/FP16/vehicle-license-plate-detection-barrier-0123.xml |
There was a problem hiding this comment.
The model is vehicle-license-plate-detection-barrier-0123.xml, but label is vehicle-license-plate-detection-barrier-0106.labels

No description provided.