{"id":23437285,"url":"https://github.com/pvnieo/deep-levi","last_synced_at":"2025-08-01T23:38:21.427Z","repository":{"id":255012326,"uuid":"128666138","full_name":"pvnieo/Deep-Levi","owner":"pvnieo","description":"Automatic colorization using deep neural networks.","archived":false,"fork":false,"pushed_at":"2020-12-15T10:39:58.000Z","size":467855,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-13T04:51:49.123Z","etag":null,"topics":["automatic-colorization","colorization","computer-vision","deep-learning","keras"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pvnieo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-04-08T17:39:19.000Z","updated_at":"2024-03-16T14:07:29.000Z","dependencies_parsed_at":"2024-08-27T14:16:54.091Z","dependency_job_id":"1dc795ce-d9ca-47a7-a01f-18233d2a4400","html_url":"https://github.com/pvnieo/Deep-Levi","commit_stats":null,"previous_names":["pvnieo/deep-levi"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pvnieo/Deep-Levi","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pvnieo%2FDeep-Levi","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pvnieo%2FDeep-Levi/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pvnieo%2FDeep-Levi/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pvnieo%2FDeep-Levi/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pvnieo","download_url":"https://codeload.github.com/pvnieo/Deep-Levi/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pvnieo%2FDeep-Levi/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259708220,"owners_count":22899556,"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":["automatic-colorization","colorization","computer-vision","deep-learning","keras"],"created_at":"2024-12-23T13:44:43.151Z","updated_at":"2025-06-13T19:37:28.088Z","avatar_url":"https://github.com/pvnieo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep-Levi\nImplementation of some automatic colorization models using deep neural network:\n\n1. Implementation of the regression-based model provided in: \"Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification\" [Link to the original paper](http://hi.cs.waseda.ac.jp/~iizuka/projects/colorization/en/)\n2.  Implementation of a classification-based model  inspired in part by Zhang et al. in \"Colorful Image Colorization\"  [[Link to the original paper](https://github.com/richzhang/colorization)] and R.Dah in [here](http://tinyclouds.org/colorize)\n3.  Implementation of a regression-based model inspired from [this Medium blog article](https://medium.freecodecamp.org/colorize-b-w-photos-with-a-100-line-neural-network-53d9b4449f8d)\n\n## Project report\nYou can consult the project report [here](https://github.com/pvnieo/Deep-Levi/blob/master/%C3%89tude%20comparative%20d%E2%80%99architecture%20de%20colorisation%20automatique.pdf) (in French)\n\n## Installation\n\nThis project runs on python \u003e= 3.6, use pip to install dependencies:\n\n```\npip3 install -r requirements.txt\n```\n\n## Usage\n\nUse the `main.py` script to choose the model to train and the parameters to use\n\n```\nusage: main.py [-h] [-m {naive,reg,classif}] [-d DATA_DIR] [-e EPOCHS]\n               [-b BATCH_SIZE] [-tc TO_COLOR] [--no-load] [--no-save]\n               [--no-train] [--early]\n\nAn implementation of multiple approachs to automatically colorize grey-scale\nimages\n\noptional arguments:\n  -h, --help            show this help message and exit\n  -m {naive,reg,classif}, --model {naive,reg,classif}\n                        Colorization model\n  -d DATA_DIR, --data-dir DATA_DIR\n                        Directory where data is\n  -e EPOCHS, --epochs EPOCHS\n                        Number of epochs to train for\n  -b BATCH_SIZE, --batch-size BATCH_SIZE\n                        Batch size to use\n  -tc TO_COLOR, --to-color TO_COLOR\n                        Number of samples to be colored\n  --no-load             Disable loading saved model\n  --no-save             Disable saving the new model\n  --no-train            Disable training the model\n  --early               Enable early stopping\n```\n\nUse the `levi.py` script to color images using a model\n\n```\nusage: levi.py -h [-d DATA_DIR]\n\nAn implementation of multiple approachs to automatically colorize grey-scale\n\nimages\n\noptional arguments:\n\n  -h, --help            show this help message and exit\n\n  -m {naive,reg,classif}, --model {naive,reg,classif}\n\n                        Colorization model\n\n  -d DATA_DIR, --data-dir DATA_DIR\n\n                        Directory where the images to be colored is\n\n```\n\n## Note\n\nThis project is under development. The final objective being to create a model that colors mangas by learning on the corresponding anime, this project will be updated regularly.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpvnieo%2Fdeep-levi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpvnieo%2Fdeep-levi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpvnieo%2Fdeep-levi/lists"}