Repository for the Video sentiment analysis module of the ESA project.
- Clone/pull project
- If it is from scratch, clone this project:
git clone https://ooti-projects.win.tue.nl/gitlab/st-c2019/esa/video-sentimental-analysis.git
- if it is from existing project, pull the project
git pull
- Follow the instructions to install DVC (on Windows):
- Linux: https://dvc.org/doc/install/linux
- MacOS: https://dvc.org/doc/install/macos
- Windows: https://dvc.org/doc/install/windows
- Follow the instructions to install aws cli version 2.
- Linux: https://docs.aws.amazon.com/cli/latest/userguide/install-cliv2-linux.html
- MacOS: https://docs.aws.amazon.com/cli/latest/userguide/install-cliv2-mac.html
- Windows: https://docs.aws.amazon.com/cli/latest/userguide/install-cliv2-windows.html
- Configure aws cli:
> aws configure
AWS Access Key ID [None]: AKIA55GEKVQR3FCPU7PV
AWS Secret Access Key [None]: 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
Default region name [None]: eu-central-1
Default output format [None]: text
- Download production data and models:
dvc pull
- Add or remove audios from the
prod_data
directory. - Execute
dvc status
to see that the contents ofprod_data
were modified. - Execute
dvc add prod_data
to update the contents ofprod_data.dvc
. - Track changes with git:
git add prod_data.dvc
. - Git commit:
git commit -m "commit message"
. - Update production:
dvc push
. - Push changes to GitLab:
git push origin [branch-name]
.
- Add new model in the
prod_models
directory. - Execute
dvc status
to see that the contents ofprod_models
were modified. - Execute
dvc add prod_models
to update the contents ofprod_models.dvc
. - Track changes with git:
git add prod_models.dvc
. - Git commit:
git commit -m "commit message"
. - Update production:
dvc push
. - Push changes to GitLab:
git push origin [branch-name]
.
- Log into the raspberry pi.
- Go to /home/pi/esaProject.
- Activate virtual environment:
source videoTeam/bin/activate
. - Go to the repository directory
cd video-sentiment-analysis
. - Pull changes from master
git pull origin master
. - Pull latest data and models using dvc
dvc pull
. - Go to the repository directory containing the source code.
- Run your script.