{"id":13719216,"url":"https://github.com/Armour/Automatic-Image-Colorization","last_synced_at":"2025-05-07T11:31:27.549Z","repository":{"id":65294684,"uuid":"75982807","full_name":"Armour/Automatic-Image-Colorization","owner":"Armour","description":"🎨 Automatic Image Colorization using TensorFlow based on Residual Encoder Network","archived":false,"fork":false,"pushed_at":"2022-09-08T21:58:21.000Z","size":40717,"stargazers_count":168,"open_issues_count":5,"forks_count":44,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-05-07T09:52:35.241Z","etag":null,"topics":["auto-colorization","colorization","gpu","image-colorization","jarvis","python3","residual-encoder-network","tensorflow"],"latest_commit_sha":null,"homepage":"http://tinyclouds.org/colorize/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Armour.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":".github/CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":".github/CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-12-08T23:10:26.000Z","updated_at":"2025-04-09T06:52:18.000Z","dependencies_parsed_at":"2023-01-18T01:30:43.537Z","dependency_job_id":null,"html_url":"https://github.com/Armour/Automatic-Image-Colorization","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Armour%2FAutomatic-Image-Colorization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Armour%2FAutomatic-Image-Colorization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Armour%2FAutomatic-Image-Colorization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Armour%2FAutomatic-Image-Colorization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Armour","download_url":"https://codeload.github.com/Armour/Automatic-Image-Colorization/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252868842,"owners_count":21816924,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["auto-colorization","colorization","gpu","image-colorization","jarvis","python3","residual-encoder-network","tensorflow"],"created_at":"2024-08-03T01:00:44.493Z","updated_at":"2025-05-07T11:31:27.500Z","avatar_url":"https://github.com/Armour.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Automatic Image Colorization\n\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat)](http://makeapullrequest.com)\n[![License: GPL v3](https://img.shields.io/badge/License-GPL%20v3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)\n[![Template from jarvis](https://img.shields.io/badge/Hi-Jarvis-ff69b4.svg)](https://github.com/Armour/Jarvis)\n\n## Overview\n\nThis is a TensorFlow implementation of the Residual Encoder Network based on [Automatic Colorization](http://tinyclouds.org/colorize/) and the pre-trained VGG16 model from [https://github.com/machrisaa/tensorflow-vgg](https://github.com/machrisaa/tensorflow-vgg)\n\n**For latest TensorFlow with [estimator](https://www.tensorflow.org/guide/estimators) support, check [tf-1.12](https://github.com/Armour/Automatic-Image-Colorization/tree/tf-1.12) branch. (still under development, the training code is working now)**\n\n## Structure\n\n* `config.py`: config variables like batch size, training_iters and so on\n* `image_helper.py`: all functions related to image manipulation\n* `read_input.py`: all functions related to input\n* `residual_encoder.py`: the residual encoder model\n* `common.py`: the common part for training and testing, which is mainly the workflow for this model\n* `train.py`: train the residual encoder model using TensorFlow built-in AdamOptimizer\n* `test.py`: test your own images and save the output images\n\n## TensorFlow graph\n\n![residual_encoder](images/residual_encoder.png)\n\n## How to use\n\n* Download pre-trained VGG16 model [vgg16.npy](https://mega.nz/#!YU1FWJrA!O1ywiCS2IiOlUCtCpI6HTJOMrneN-Qdv3ywQP5poecM) to vgg folder\n\n* Option 1: Use pre-trained residual encoder model\n  * Download model [here](https://github.com/Armour/Automatic-Image-Colorization/releases/tag/2.0)\n  * Unzip all files to `summary_path` (you can change this path in `config.py`)\n\n* Option 2: Train your own model!\n  1. Change the `batch_size` and `training_iters` if you want.\n  2. Change `training_dir` to your directory that has all your training jpg images\n  3. Run `python train.py`\n\n* Test\n  1. Change `testing_dir` to your directory that has all your testing jpg images\n  2. Run `python test.py`\n\n## Examples\n\n* ![1](images/1.png)\n* ![2](images/2.png)\n* ![3](images/3.png)\n* ![4](images/4.png)\n* ![5](images/5.png)\n* ![6](images/6.png)\n* ![7](images/7.png)\n* ![8](images/8.png)\n* ![9](images/9.png)\n* ![10](images/10.png)\n* ![11](images/11.png)\n* ![12](images/12.png)\n\n* More example output images can be found in [sample_output_images](https://github.com/Armour/Automatic-Image-Colorization/blob/master/sample_output_images) folder.\n\n## References\n\n* [Automatic Colorization](http://tinyclouds.org/colorize/)\n* [pavelgonchar/colornet](https://github.com/pavelgonchar/colornet)\n* [raghavgupta0296/ColourNet](https://github.com/raghavgupta0296/ColourNet)\n* [pretrained VGG16 npy file](https://github.com/machrisaa/tensorflow-vgg)\n\n## Contributing\n\nSee [CONTRIBUTING.md](https://github.com/Armour/Automatic-Image-Colorization/blob/master/.github/CONTRIBUTING.md)\n\n## License\n\n[GNU GPL 3.0](https://github.com/Armour/Automatic-Image-Colorization/blob/master/LICENSE) for personal or research use. COMMERCIAL USE PROHIBITED.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FArmour%2FAutomatic-Image-Colorization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FArmour%2FAutomatic-Image-Colorization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FArmour%2FAutomatic-Image-Colorization/lists"}