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 details)

Uploaded Source

Built Distribution

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

Uploaded Python 3

File details

Details for the file yolo_labeler-0.0.3.tar.gz.

File metadata

  • Download URL: yolo_labeler-0.0.3.tar.gz
  • Upload date:
  • Size: 10.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.24.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.48.2 CPython/3.8.5

File hashes

Hashes for yolo_labeler-0.0.3.tar.gz
Algorithm Hash digest
SHA256 bdfc4c52e87e0f6e433c865e3096f89ea9f95d82e90d67ce2bed4722f958c322
MD5 b4a2386c8d3dac5ac89f0153e15046d5
BLAKE2b-256 356ac12884875ed22c1cb265ca4d5f9a3149f952c113e9604e984289dfbbb0bd

See more details on using hashes here.

File details

Details for the file yolo_labeler-0.0.3-py3-none-any.whl.

File metadata

  • Download URL: yolo_labeler-0.0.3-py3-none-any.whl
  • Upload date:
  • Size: 10.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.6.1 requests/2.24.0 setuptools/50.3.2 requests-toolbelt/0.9.1 tqdm/4.48.2 CPython/3.8.5

File hashes

Hashes for yolo_labeler-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 c5e75d3d2837044aa58043cf64644b47aaa4935401e52554a865041f7834e3c9
MD5 59ad5fc63fe1bbf69bd76e84051ad66a
BLAKE2b-256 711e6fca5d6a6ee0ed3dc46af671d4ce6d3e1a7c12ba22736719bca063250a9f

See more details on using hashes here.

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