{"id":19068707,"url":"https://github.com/machine-learning-tokyo/poetry-gan","last_synced_at":"2025-04-28T13:35:03.683Z","repository":{"id":55819376,"uuid":"160933046","full_name":"Machine-Learning-Tokyo/Poetry-GAN","owner":"Machine-Learning-Tokyo","description":null,"archived":false,"fork":false,"pushed_at":"2019-10-31T03:54:53.000Z","size":2584,"stargazers_count":50,"open_issues_count":1,"forks_count":11,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-04-18T16:26:06.311Z","etag":null,"topics":["creativity","generative-adversarial-network","machine-learning","nlp","research"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/Machine-Learning-Tokyo.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":"2018-12-08T11:36:37.000Z","updated_at":"2024-10-29T23:33:23.000Z","dependencies_parsed_at":"2022-08-15T07:21:13.739Z","dependency_job_id":null,"html_url":"https://github.com/Machine-Learning-Tokyo/Poetry-GAN","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/Machine-Learning-Tokyo%2FPoetry-GAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Machine-Learning-Tokyo%2FPoetry-GAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Machine-Learning-Tokyo%2FPoetry-GAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Machine-Learning-Tokyo%2FPoetry-GAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Machine-Learning-Tokyo","download_url":"https://codeload.github.com/Machine-Learning-Tokyo/Poetry-GAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251320405,"owners_count":21570571,"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":["creativity","generative-adversarial-network","machine-learning","nlp","research"],"created_at":"2024-11-09T01:11:29.948Z","updated_at":"2025-04-28T13:35:03.622Z","avatar_url":"https://github.com/Machine-Learning-Tokyo.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Creative GANs\nCreative GANs is a research project on training language models to generate creative text with either a Maximum Likelihood Estimation (MLE) or GAN objective. It contains the code for running the experiments as described in the [paper](https://arxiv.org/abs/1909.09534). \n\nSome curated outputs can be found [here](https://www.ai-fragments.com/)\n\n## Datasets\n- Gutenberg Novels\n- English poetry\n- Song lyrics\n- [Metaphors](http://metaphors.iath.virginia.edu/metaphors)\n\n## Text Generative Models with LM and GAN objective\n- AWD LSTM [paper link](https://arxiv.org/pdf/1708.02182.pdf)\n- Transformer XL [paper link](https://arxiv.org/pdf/1901.02860.pdf)\n\nThe encoder models are from the fastai library\n\n## Usage\n- Preprocess data `python preprocess.py [gutenberg/metaphors/poems/lyrics]` and save preprocessed file\n- Train language model `lang_model.py PATH FILENAME MODEL [PRETRAINED_FNAMES]`\n- Train gan model `textgan.py PATH FILENAME PRETRAINED MODEL [CRIT] [PREDS] [EPOCHS]`\n\n```\nPATH - folder with data \nFILENAME - name of preprocessed file\nPRETRAINED - fastai model saved with learn.save()\nPRETRAINED_FNAMES - pretrained weight file and vocab file (comma seperated)\nMODEL - architecture to use {'AWD': AWD_LSTM, 'XL':TransformerXL}\nCRIT - loss function: gumbel softmax/reinforce (only for gan)\nPREDS - generate output from validation set \nEPOCHS - number of epochs to train\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmachine-learning-tokyo%2Fpoetry-gan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmachine-learning-tokyo%2Fpoetry-gan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmachine-learning-tokyo%2Fpoetry-gan/lists"}