https://github.com/guillainbisimwa/intel-edge-ai-foundation-course
Intel Edge AI Scholarship Foundation Course, OpenVINO Fundamentals! #celebrateyoursuccess #madebyudacity #intel @udacity #Edge #AI
https://github.com/guillainbisimwa/intel-edge-ai-foundation-course
Last synced: 7 months ago
JSON representation
Intel Edge AI Scholarship Foundation Course, OpenVINO Fundamentals! #celebrateyoursuccess #madebyudacity #intel @udacity #Edge #AI
- Host: GitHub
- URL: https://github.com/guillainbisimwa/intel-edge-ai-foundation-course
- Owner: guillainbisimwa
- Created: 2019-12-27T15:40:32.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2022-12-12T02:30:05.000Z (almost 3 years ago)
- Last Synced: 2025-01-30T05:42:51.690Z (9 months ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 85.7 MB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 40
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
---
noteId: "fe871370b4a911eba09fc3f786392703"
tags: []
---
# Intel-Edge-AI-Foundation-Course
Use the image in another container
You can use this Docker image as a base image and use it in multiple Dockerfiles. An example of how to do this has been provided:
Move to sample-app directory and build the image
```bash
docker build -t intel-edge .
```
Run the the container with X enabled (Linux)
Additionally, for running a intel-edge application that displays an image, you need to share the host display to be accessed from guest Docker container.
The X server on the host should be enabled for remote connections:
```bash
xhost +
```
The following flags needs to be added to the docker run command:
```bash
--net=host
--env="DISPLAY"
--volume="$HOME/.Xauthority:/root/.Xauthority:rw"
```
To run the intel-edge image with the display enabled:
```bash
docker run --net=host --env="DISPLAY" --volume="$HOME/.Xauthority:/root/.Xauthority:rw" -ti d9c72c1ee970 /bin/bash
```
Finally disable the remote connections to the X server
```bash
xhost -
```
### Use the image in another container
You can use this Docker image as a base image and use it in multiple Dockerfiles. An example of how to do this has been provided:
Move to root directory and build the image
```bash
cd root directory
docker build -t my-intel-edge .
```
### Run a container
You can directly run a container based on this image or use this image across other images.
To run a container based on this image:
```bash
docker run -ti d9c72c1ee970 /bin/bash
```
# Choosing Models
I chose the following models for the three tasks:
Human Pose Estimation: human-pose-estimation-0001
Text Detection: text-detection-0004
Determining Car Type & Color: vehicle-attributes-recognition-barrier-0039
Downloading Models
To navigate to the directory containing the Model Downloader:
```bash
cd /opt/intel/openvino/deployment_tools/open_model_zoo/tools/downloader
```
Within there, you'll notice a downloader.py file, and can use the -h argument with it to see available arguments. For this exercise, --name for model name, and --precisions, used when only certain precisions are desired, are the important arguments. Note that running downloader.py without these will download all available pre-trained models, which will be multiple gigabytes. You can do this on your local machine, if desired, but the workspace will not allow you to store that much information.
Note: In the classroom workspace, you will not be able to write to the /opt/intel directory, so you should also use the -o argument to specify your output directory as /home/workspace (which will download into a created intel folder therein).
Downloading Human Pose Model
```bash
sudo ./downloader.py --name human-pose-estimation-0001 -o /home/workspace
```
```bash
sudo ./downloader.py --name text-detection-0004 --precisions FP16 -o /home/workspace
```
```bash
sudo ./downloader.py --name vehicle-attributes-recognition-barrier-0039 --precisions INT8 -o /home/workspace
```
# Copying files from host to Docker container
## From a container to the host
```bash
docker cp CONTAINER_ID:./bar/foo.txt .
```
## From the host to a container
```bash
docker exec -i CONTAINER_ID sh -c 'cat > ./bar/foo.txt' < ./foo.txt
```
# Commit a container with new configurations
```bash
sudo docker commit --change "ENV DEBUG true" CONTAINER_ID my_name/my_image:version3
```
```bash
sudo docker commit --change "ENV DEBUG true" fb63594bf93b guillainbisimwa/openvino:version4
```
# To access the camera inside docker ( ls -ltrh /dev/video\* )
```bash
docker run --net=host --env="DISPLAY" --volume="$HOME/.Xauthority:/root/.Xauthority:rw" -v /dev/video1:/dev/video1 -ti b213c7e52101 /bin/bash
```
```bash
docker run --net=host --env="DISPLAY" --volume="$HOME/.Xauthority:/root/.Xauthority:rw" --device=/dev/video0:/dev/video0 -ti 05d6111af32e /bin/bash
```