yurijmikhalevich / rtag

AI-Powered Command-Line Photo Tagging Tool

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

rtag - AI-Powered Command-Line Photo Tagging Tool

NOTICE: rtag is under active development. Expect bugs and changes.

rtag is a command-line photo tagging tool based on rclip and powered by the awesome OpenAI's CLIP neural network.

Usage

When run without arguments, rtag tags all of the images in the current directory, including subdirectories, with the most relevant tags out of the imagenet-1k tag list. rtag writes the tags to the images' metadata, in a format supported by most photo management software. rtag supports JPG images only.

cd photos && rtag

How do I use my own tag list?

You can use your own tag list by providing a path to a file with tags as an argument to rtag.

cd photos && rtag --tags-filepath /path/to/your/tag/list.txt

The tag list file should contain one tag per line.

You can also adjust a --threshold used to filter out tags with a lower confidence score. Run rtag in the --dry-run mode to see the confidence scores for each tag that passes the threshold.

Help

rtag --help

Contributing

This repository follows the Conventional Commits standard.

Running locally from the source code

To run rtag locally from the source code, you must have Python and Poetry installed.

Then do:

# clone the source code repository
git clone git@github.com:yurijmikhalevich/rtag.git

# install dependencies and rtag
cd rtag
poetry install

# activate the new poetry environment
poetry shell

If the poetry environment is active, you can use rtag locally, as described in the Usage section above.

About

AI-Powered Command-Line Photo Tagging Tool

License:MIT License


Languages

Language:Python 100.0%