{"id":13512297,"url":"https://github.com/OsciiArt/DeepAA","last_synced_at":"2025-03-30T22:32:29.362Z","repository":{"id":44422659,"uuid":"83964481","full_name":"OsciiArt/DeepAA","owner":"OsciiArt","description":"make ASCII Art by Deep Learning","archived":false,"fork":false,"pushed_at":"2021-07-14T02:47:40.000Z","size":19983,"stargazers_count":1535,"open_issues_count":2,"forks_count":102,"subscribers_count":39,"default_branch":"master","last_synced_at":"2025-03-25T18:18:40.237Z","etag":null,"topics":["ascii-art","deep-learning","keras","python","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/OsciiArt.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}},"created_at":"2017-03-05T11:18:43.000Z","updated_at":"2025-03-16T19:51:01.000Z","dependencies_parsed_at":"2022-08-27T05:01:41.045Z","dependency_job_id":null,"html_url":"https://github.com/OsciiArt/DeepAA","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OsciiArt%2FDeepAA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OsciiArt%2FDeepAA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OsciiArt%2FDeepAA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OsciiArt%2FDeepAA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OsciiArt","download_url":"https://codeload.github.com/OsciiArt/DeepAA/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246390883,"owners_count":20769475,"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":["ascii-art","deep-learning","keras","python","tensorflow"],"created_at":"2024-08-01T03:01:42.114Z","updated_at":"2025-03-30T22:32:24.353Z","avatar_url":"https://github.com/OsciiArt.png","language":"Python","readme":"DeepAA\n====\n\nThis is convolutional neural networks generating ASCII art.\nThis repository is under construction.\n\nThis work is accepted by [NIPS 2017 Workshop, Machine Learning for Creativity and Design](https://nips2017creativity.github.io/)\nThe paper: [ASCII Art Synthesis with Convolutional Networks](https://nips2017creativity.github.io/doc/ASCII_Art_Synthesis.pdf)\n\n[Web application (using previous version model)](https://tar-bin.github.io/DeepAAonWeb/) (by [tar-bin](https://github.com/tar-bin))\n\n![image sample](https://github.com/OsciiArt/DeepAA/blob/master/sample%20images/images%20generated%20with%20CNN/21%20generated.png)\n\n\n## Change log\n+ 2017/12/2 added light model\n## Requirements\n\n+ TensorFlow (1.3.0)\n+ Keras (2.0.8)\n+ NumPy (1.13.3)\n+ Pillow (4.2.1)\n+ Pandas (0.18.0)\n+ Scikit-learn (0.19.0)\n+ h5py (2.7.1)\n+ model's weight (download it from [here](https://drive.google.com/open?id=0B90WglS_AQWebjBleG5uRXpmbUE) and place it in dir `model`.)\n+ training data (additional, download it from  [here](https://drive.google.com/open?id=1L5n5ICrsXtsWkT-aq2et1FTzp-RH3CeS), extract it and place the extracted directory in dir `data`.)\n)\n\n## How to use\nplease change the line 15 of `output.py `\n\n```\nimage_path = 'sample images/original images/21 original.png' # put the path of the image that you convert.\n```\ninto the path of image file that you use.\nYou should use a grayscale line image.\n\nthen run `output.py `.\nconverted images will be output at `output/ `.\n\nYou can select light model by change the line 13, 14  of `output.py ` into\n```\nmodel_path = \"model/model_light.json\"\nweight_path = \"model/weight_light.hdf5\"\n```\n## License\nThe pre-trained models and the other files we have provided are licensed under the MIT License.\n","funding_links":[],"categories":["Python","Image Generation"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOsciiArt%2FDeepAA","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FOsciiArt%2FDeepAA","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOsciiArt%2FDeepAA/lists"}