{"id":13487106,"url":"https://github.com/tensorflow/fold","last_synced_at":"2025-04-08T08:12:13.808Z","repository":{"id":43675863,"uuid":"79366567","full_name":"tensorflow/fold","owner":"tensorflow","description":"Deep learning with dynamic computation graphs in TensorFlow","archived":false,"fork":false,"pushed_at":"2021-06-26T15:49:57.000Z","size":1605,"stargazers_count":1824,"open_issues_count":58,"forks_count":267,"subscribers_count":99,"default_branch":"master","last_synced_at":"2025-04-01T05:33:33.991Z","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tensorflow.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-01-18T17:45:53.000Z","updated_at":"2025-03-17T21:35:13.000Z","dependencies_parsed_at":"2022-09-02T15:20:20.796Z","dependency_job_id":null,"html_url":"https://github.com/tensorflow/fold","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/tensorflow%2Ffold","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorflow%2Ffold/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorflow%2Ffold/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorflow%2Ffold/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tensorflow","download_url":"https://codeload.github.com/tensorflow/fold/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247801170,"owners_count":20998339,"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":"2024-07-31T18:00:55.459Z","updated_at":"2025-04-08T08:12:13.792Z","avatar_url":"https://github.com/tensorflow.png","language":"Python","readme":"# TensorFlow Fold\n\nTensorFlow Fold is a library for\ncreating [TensorFlow](https://www.tensorflow.org) models that consume structured\ndata, where the structure of the computation graph depends on the structure of\nthe input data. For example, [this model](tensorflow_fold/g3doc/sentiment.ipynb)\nimplements [TreeLSTMs](https://arxiv.org/abs/1503.00075) for sentiment analysis\non parse trees of arbitrary shape/size/depth.\n\nFold implements [*dynamic batching*](https://arxiv.org/abs/1702.02181).\nBatches of arbitrarily shaped computation graphs are transformed to produce a\nstatic computation graph. This graph has the same structure regardless of what\ninput it receives, and can be executed efficiently by TensorFlow.\n\n* [Download and Setup](tensorflow_fold/g3doc/setup.md)\n* [Quick Start Notebook](tensorflow_fold/g3doc/quick.ipynb)\n* [Documentation](tensorflow_fold/g3doc/index.md)\n\n![animation](tensorflow_fold/g3doc/animation.gif)  \n\nThis animation shows a [recursive neural network](https://en.wikipedia.org/wiki/Recursive_neural_network) run with dynamic batching. Operations of the same type appearing at the same depth in the computation graph (indicated by color in the animiation) are batched together regardless of whether or not they appear in the same parse tree. The [Embed](tensorflow_fold/g3doc/py/td.md#td.Embedding) operation converts [words to vector representations](https://www.tensorflow.org/tutorials/word2vec/). The fully connected ([FC](tensorflow_fold/g3doc/py/td.md#td.FC)) operation combines word vectors to form vector representations of phrases. The output of the network is a vector representation of an entire sentence.  Although only a single parse tree of a sentence is shown, the same network can run, and batch together operations, over multiple parse trees of arbitrary shapes and sizes. The TensorFlow `concat`, `while_loop`, and `gather` ops are created once, prior to variable initialization, by [Loom](tensorflow_fold/g3doc/py/loom.md), the low-level API for TensorFlow Fold.\n\nIf you'd like to contribute to TensorFlow Fold, please review the\n[contribution guidelines](CONTRIBUTING.md).\n  \nTensorFlow Fold is not an official Google product.\n","funding_links":[],"categories":["Python","The Data Science Toolbox","Deep Learning","Tensor Flow"],"sub_categories":["Deep Learning Packages","TensorFlow","Automated Machine Learning"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftensorflow%2Ffold","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftensorflow%2Ffold","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftensorflow%2Ffold/lists"}