{"id":13526170,"url":"https://github.com/kefirski/pytorch_RVAE","last_synced_at":"2025-04-01T06:31:30.087Z","repository":{"id":67900247,"uuid":"81716744","full_name":"kefirski/pytorch_RVAE","owner":"kefirski","description":"Recurrent Variational Autoencoder that generates sequential data implemented with pytorch","archived":false,"fork":false,"pushed_at":"2017-03-15T07:23:52.000Z","size":1874,"stargazers_count":356,"open_issues_count":12,"forks_count":89,"subscribers_count":10,"default_branch":"master","last_synced_at":"2024-05-23T02:33:26.651Z","etag":null,"topics":["deep-learning","nlp","python","pytorch","vae"],"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/kefirski.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}},"created_at":"2017-02-12T09:54:09.000Z","updated_at":"2024-03-30T13:41:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"7f556eba-b9a8-485f-ab05-18609f748712","html_url":"https://github.com/kefirski/pytorch_RVAE","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/kefirski%2Fpytorch_RVAE","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kefirski%2Fpytorch_RVAE/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kefirski%2Fpytorch_RVAE/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kefirski%2Fpytorch_RVAE/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kefirski","download_url":"https://codeload.github.com/kefirski/pytorch_RVAE/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222703737,"owners_count":17025838,"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":["deep-learning","nlp","python","pytorch","vae"],"created_at":"2024-08-01T06:01:26.065Z","updated_at":"2024-11-02T10:31:42.113Z","avatar_url":"https://github.com/kefirski.png","language":"Python","funding_links":[],"categories":["Paper Implementations"],"sub_categories":[],"readme":"# Pytorch Recurrent Variational Autoencoder \n\n## Model:\nThis is the implementation of Samuel Bowman's [Generating Sentences from a Continuous Space](https://arxiv.org/abs/1511.06349#)\nwith Kim's [Character-Aware Neural Language Models](https://arxiv.org/abs/1508.06615) embedding for tokens\n\n## Sampling examples:\n\u003e the new machine could be used to increase the number of ventures block in the company 's \\\u003cunk\u003e shopping system to finance diversified organizations\n\n\u003e u.s. government officials also said they would be willing to consider whether the proposal could be used as urging and programs\n\n\u003e men believe they had to go on the \\\u003cunk\u003e because their \\\u003cunk\u003e were \\\u003cunk\u003e expensive important\n\n\u003e the companies insisted that the color set could be included in the program\n\n## Usage\n### Before model training it is necessary to train word embeddings:\n```\n$ python train_word_embeddings.py\n```\n\nThis script train word embeddings defined in [Mikolov et al. Distributed Representations of Words and Phrases](https://arxiv.org/abs/1310.4546)\n\n#### Parameters:\n`--use-cuda`\n\n`--num-iterations`\n\n`--batch-size`\n\n`--num-sample` –– number of sampled from noise tokens\n\n\n### To train model use:\n```\n$ python train.py\n```\n\n#### Parameters:\n`--use-cuda`\n\n`--num-iterations`\n\n`--batch-size`\n\n`--learning-rate`\n \n`--dropout` –– probability of units to be zeroed in decoder input\n\n`--use-trained` –– use trained before model\n\n### To sample data after training use:\n```\n$ python sample.py\n```\n#### Parameters:\n`--use-cuda`\n\n`--num-sample`\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkefirski%2Fpytorch_RVAE","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkefirski%2Fpytorch_RVAE","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkefirski%2Fpytorch_RVAE/lists"}