Skip to main content

Remove image background and label object in yolo format

Project description

Automatic YOLO Labeler

License

Note: Tool works for single object per image only. Please use images with single object for accurate results. You can verify labels by checking png images. If the background is correctly removed from image then it is labelled correctly.

YOLO Labeler is a tool to remove images background and label object in YOLO format.

Examples

YOLO String: 0 0.513942 0.407692 0.272115 0.746795

YOLO String: 0 0.287500 0.580769 0.575000 0.837821

YOLO String: 1 0.546627 0.473380 0.899471 0.834987

YOLO String: 2 0.312660 0.499840 0.625321 0.999679

YOLO String: 2 0.484135 0.499840 0.363141 0.999679

Installation

pip3 install yolo-labeler

Usage as a library

In test.py

from yolo_labeler import yolo_labeler

yolo_labeler.run(args)

run command

python3 test.py --input_path /path/to/input/image or image_folder --output_image_path /path/to/output/images --output_text_path /path/to/output/text --yolo_label class_num

Advance usage

To not resize images provide --resize flag to 1

python3 test.py --input_path /path/to/input/image or image_folder --output_image_path /path/to/output/images --output_text_path /path/to/output/text --yolo_label class_num --size 1

To save output png images provide --png_path

python3 test.py --input_path /path/to/input/image or image_folder --output_image_path /path/to/output/images --output_text_path /path/to/output/text --yolo_label class_num --size 1 --png_path /path/to/output/png

To resize images of custom width x height provide --width and --height. Default is 416x416

python3 test.py --input_path /path/to/input/image or image_folder --output_image_path /path/to/output/images --output_text_path /path/to/output/text --yolo_label class_num --png_path /path/to/output/png --width 416 --height 416

To change background behind object provide --background_image

python3 test.py --input_path /path/to/input/image or image_folder --output_image_path /path/to/output/images --output_text_path /path/to/output/text --yolo_label class_num --png_path /path/to/output/png --width 1000 --height 1000 --background_image /path/to/background/image

To save changed background images provide --background_out

python3 test.py --input_path /path/to/input/image or image_folder --output_image_path /path/to/output/images --output_text_path /path/to/output/text --yolo_label class_num --png_path /path/to/output/png --width 416 --height 416 --background_image /path/to/background/image --background_out /path/to/output/changed/background/images

References

License

Copyright (c) 2020-present Abhi Panchal

Licensed under MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

yolo_labeler-0.0.3.tar.gz (10.5 kB view hashes)

Uploaded Source

Built Distribution

yolo_labeler-0.0.3-py3-none-any.whl (10.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page