{"id":13660881,"url":"https://github.com/ssemeniuta/textvae","last_synced_at":"2025-04-24T23:30:57.855Z","repository":{"id":217149345,"uuid":"81260621","full_name":"ssemeniuta/textvae","owner":"ssemeniuta","description":"Theano code for experiments in the paper \"A Hybrid Convolutional Variational Autoencoder for Text Generation.\"","archived":false,"fork":false,"pushed_at":"2018-10-05T18:54:16.000Z","size":31,"stargazers_count":205,"open_issues_count":3,"forks_count":45,"subscribers_count":11,"default_branch":"master","last_synced_at":"2024-11-10T15:44:37.548Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ssemeniuta.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2017-02-07T22:19:35.000Z","updated_at":"2024-08-12T19:27:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"4253859e-d0c6-4891-8452-ee913c69f36c","html_url":"https://github.com/ssemeniuta/textvae","commit_stats":null,"previous_names":["ssemeniuta/textvae"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssemeniuta%2Ftextvae","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssemeniuta%2Ftextvae/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssemeniuta%2Ftextvae/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssemeniuta%2Ftextvae/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ssemeniuta","download_url":"https://codeload.github.com/ssemeniuta/textvae/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250727501,"owners_count":21477322,"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":[],"created_at":"2024-08-02T05:01:26.925Z","updated_at":"2025-04-24T23:30:57.526Z","avatar_url":"https://github.com/ssemeniuta.png","language":"Python","readme":"####  A Hybrid Convolutional Variational Autoencoder for Text Generation.\n\nTheano code for experiments in the paper [A Hybrid Convolutional Variational Autoencoder for Text Generation](https://arxiv.org/abs/1702.02390).\n\n#### Preparation\n\nFirst, run makedata.sh. This will download the ptb dataset, split, and preprocess it.\n\n#### PTB Experiments\n\nFiles prefixed with ''lm_'' contain experiments on the ptb dataset. We provide scripts for training of non-VAE, baseline LSTM VAE, and our models and a script to greedily sample from a trained model. ''defs'' subfolder contains definitions of grid searches we have used to generate data for figures and tables in the paper. Running one search is done by:\n```bash\npython -u nn/scripts/grid_search.py -grid defs/gridname.json\n```\nTo train our model on samples 60 characters long with alpha=0.2 run:\n```bash\npython -u lm_vae_lstm.py -alpha 0.2 -sample_size 60\n```\n\n#### Twitter Experiments\n\nCode for these experiments is in files starting with ''twitter_''. We do not release the dataset we have used to train our model, but provide both a script to train one and [a pretrained model](https://www.dropbox.com/s/lv20o4gbkwvy097/pretrained.tar?dl=1). To use the script on custom data, create a file ''data/tweets.txt'' containing one data sample per line. By default, the first 10k samples will be used for validation and everything else for training, but no more than ~1M samples. In addition, it will only use tweets with up to 128 characters. This is done only for convenience when down- and upsampling. Training on tweets with up to 140 characters will require a little bit of care when handling spatial dimension.\n\n#### License\n\nMIT\n","funding_links":[],"categories":["Python"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fssemeniuta%2Ftextvae","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fssemeniuta%2Ftextvae","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fssemeniuta%2Ftextvae/lists"}