{"id":44902923,"url":"https://github.com/ofirnachum/tree_rnn","last_synced_at":"2026-03-02T15:00:30.430Z","repository":{"id":80164424,"uuid":"57269681","full_name":"ofirnachum/tree_rnn","owner":"ofirnachum","description":"Theano implementation of Tree RNNs aka Recursive Neural Networks.","archived":false,"fork":false,"pushed_at":"2016-08-15T16:17:26.000Z","size":25,"stargazers_count":236,"open_issues_count":3,"forks_count":50,"subscribers_count":29,"default_branch":"master","last_synced_at":"2023-10-20T22:09:34.167Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/ofirnachum.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}},"created_at":"2016-04-28T03:59:50.000Z","updated_at":"2023-10-20T22:09:35.811Z","dependencies_parsed_at":null,"dependency_job_id":"9a3a8eef-688b-4a39-9277-dd418699e0af","html_url":"https://github.com/ofirnachum/tree_rnn","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/ofirnachum/tree_rnn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ofirnachum%2Ftree_rnn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ofirnachum%2Ftree_rnn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ofirnachum%2Ftree_rnn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ofirnachum%2Ftree_rnn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ofirnachum","download_url":"https://codeload.github.com/ofirnachum/tree_rnn/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ofirnachum%2Ftree_rnn/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30007043,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-02T14:08:50.421Z","status":"ssl_error","status_checked_at":"2026-03-02T14:08:50.037Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":"2026-02-17T22:01:18.263Z","updated_at":"2026-03-02T15:00:30.424Z","avatar_url":"https://github.com/ofirnachum.png","language":"Python","funding_links":[],"categories":["Uncategorized"],"sub_categories":["Uncategorized"],"readme":"# tree_rnn\nTheano implementation of Tree RNNs aka Recursive Neural Networks.\n\nIncludes implementation of TreeLSTMs as described in \"Improved\nSemantic Representations From Tree-Structured Long Short-Term\nMemory Networks\" by Kai Sheng Tai, Richard Socher, and Christopher\nD. Manning.\n\nAlso includes implementation of TreeGRUs derived using similar\nmethods.\n\nYou may immediately run \"dummy\" demos via simple_demo.py and\nmodulo_demo.py.\n\nCode for evaluation on the Stanford Sentiment Treebank (used by\nthe paper) is also available in sentiment.py.  To run this, you'll\nneed to download the relevant data.\n\nStep-by-step for cloning this repo and getting the sentiment model\nrunning:\n\nFrom your shell, run\n\n    git clone https://github.com/ofirnachum/tree_rnn.git\n    git clone https://github.com/stanfordnlp/treelstm.git\n    cd treelstm\n    ./fetch_and_preprocess.sh\n\nThis will download the datasets, the word vectors, and do some\npreprocessing on the data.  Once this is complete, go into the\ntree_rnn directory and start a Python shell.  In that shell,\nwe'll preprocess the word vectors:\n\n    import data_utils\n    vocab = data_utils.Vocab()\n    vocab.load('../treelstm/data/sst/vocab-cased.txt')\n    words, embeddings = \\\n        data_utils.read_embeddings_into_numpy(\n            '../treelstm/data/glove/glove.840B.300d.txt', vocab=vocab)\n\n    import numpy as np\n    np.save('../treelstm/data/words.npy', words)\n    np.save('../treelstm/data/glove.npy', embeddings)\n\nAfter exiting the Python shell, you can run the sentiment training\ndirectly\n\n    python sentiment.py\n\nThe first couple lines of output should be\n\n    train 6920\n    dev 872\n    test 1821\n    num emb 21701\n    num labels 3\n    epoch 0\n    avg loss 16.7419t example 6919 of 6920\n    dev score 0.586009174312\n    epoch 1\n    avg loss 13.8955t example 6919 of 6920\n    dev score 0.69495412844\n    epoch 2\n    avg loss 12.9191t example 6919 of 6920\n    dev score 0.730504587156\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fofirnachum%2Ftree_rnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fofirnachum%2Ftree_rnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fofirnachum%2Ftree_rnn/lists"}