rpi-docker-ros-tensorflow

Now including ROS, tensorflow/models for Object Detection API and MobileNet for Detection

Fork: romilly/rpi-docker-tensorflow

Build instructions

1. Install Docker on your Raspberry Pi.
2. curl -sSL get.docker.com | sh
3. sudo usermod -aG docker pi
4. log out, then log back in again for the change to take effect
5. sudo systemctl start docker
6. Clone this repository into a directory of your choice
7. git clone https://github.com/esahin90/rpi-docker-ros-tensorflow.git
8. Build the image
9. cd rpi-docker-tensorflow/build-tensor-pi/
10. docker build -t='yourName/rpi-docker-tensorflow' .

Running the image for Detection and Web-Video-Server

docker run -p 8080:8080 --device /dev/yourCamera yourName/ros-tensor

Running the image for Jupyter Notebook

This run instruction expects a directory called myNotebooks within your home directory.

If you save an IPython notebook to the myNotebooks sub-directory while running your container, it will get saved to the myNotebooks directory on your Pi.

Notebooks saved to that directory will be persistent - in other words, they will still be there when the container is stopped and restarted.

docker run -it -p 8888:8888 -v ~/myNotebooks:/notebooks/myNotebooks yourName/ros-tensorflow /run_jupyter.sh

Connecting to the notebooks

Open a browser on http://raspberrypi:PORT where raspberrypi is the hostname of the Pi on which the docker image is running, or on http://localhost:PORT on the Pi itself.

Port

8080 - Web-Video-Server

8888 - Jupyter Notebook

Stopping the image

docker ps
docker stop containerID

or

CTRL-C for Jupyter Notebook

Sources

1. Docker: http://blog.alexellis.io/getting-started-with-docker-on-raspberry-pi/
2. Base image: from fjctp/armf-ros-kinetic-base
3. Pi tensorflow whl file from Sam Abrahm's Github project
4. Notebooks and notebook config from The Tensorflow Docker Build on Github
5. Fork: from romilly/rpi-docker-tensorflow
6. SSD MobileNet v1 coco
7. ROS Package: cv_camera, cv_bridge, web_video_server