{"id":13562222,"url":"https://github.com/harvardnlp/pytorch-struct","last_synced_at":"2025-05-15T07:05:35.402Z","repository":{"id":35440345,"uuid":"204547575","full_name":"harvardnlp/pytorch-struct","owner":"harvardnlp","description":"Fast, general, and tested differentiable structured prediction in PyTorch","archived":false,"fork":false,"pushed_at":"2022-04-20T08:21:20.000Z","size":8667,"stargazers_count":1112,"open_issues_count":31,"forks_count":92,"subscribers_count":31,"default_branch":"master","last_synced_at":"2025-04-14T12:59:18.946Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://harvardnlp.github.io/pytorch-struct","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/harvardnlp.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":"2019-08-26T19:34:30.000Z","updated_at":"2025-04-07T14:02:22.000Z","dependencies_parsed_at":"2022-08-08T08:01:35.331Z","dependency_job_id":null,"html_url":"https://github.com/harvardnlp/pytorch-struct","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harvardnlp%2Fpytorch-struct","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harvardnlp%2Fpytorch-struct/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harvardnlp%2Fpytorch-struct/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harvardnlp%2Fpytorch-struct/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/harvardnlp","download_url":"https://codeload.github.com/harvardnlp/pytorch-struct/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254292041,"owners_count":22046426,"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":"2024-08-01T13:01:05.909Z","updated_at":"2025-05-15T07:05:30.391Z","avatar_url":"https://github.com/harvardnlp.png","language":"Jupyter Notebook","readme":"# Torch-Struct: Structured Prediction Library \n\n\n![Tests](https://github.com/harvardnlp/pytorch-struct/workflows/Tests/badge.svg)\n[![Coverage Status](https://coveralls.io/repos/github/harvardnlp/pytorch-struct/badge.svg?branch=master)](https://coveralls.io/github/harvardnlp/pytorch-struct?branch=master)\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/harvardnlp/pytorch-struct/raw/master/download.png\"\u003e\n  \u003c/p\u003e\n\n\nA library of tested, GPU implementations of core structured prediction algorithms for deep learning applications.\n\n* HMM / LinearChain-CRF \n* HSMM / SemiMarkov-CRF \n* Dependency Tree-CRF \n* PCFG Binary Tree-CRF \n* ...\n\nDesigned to be used as efficient batched layers in other PyTorch code. \n\n[Tutorial paper](https://arxiv.org/abs/2002.00876) describing methodology.\n\n## Getting Started\n\n\n```python\n!pip install -qU git+https://github.com/harvardnlp/pytorch-struct\n# Optional CUDA kernels for FastLogSemiring\n!pip install -qU git+https://github.com/harvardnlp/genbmm\n# For plotting.\n!pip install -q matplotlib\n```\n\n\n```python\nimport torch\nfrom torch_struct import DependencyCRF, LinearChainCRF\nimport matplotlib.pyplot as plt\ndef show(x): plt.imshow(x.detach())\n```\n\n\n```python\n# Make some data.\nvals = torch.zeros(2, 10, 10) + 1e-5\nvals[:, :5, :5] = torch.rand(5)\nvals[:, 5:, 5:] = torch.rand(5) \ndist = DependencyCRF(vals.log())\nshow(dist.log_potentials[0])\n```\n\n\n![png](README_files/README_4_0.png)\n\n\n\n```python\n# Compute marginals\nshow(dist.marginals[0])\n```\n\n\n![png](README_files/README_5_0.png)\n\n\n\n```python\n# Compute argmax\nshow(dist.argmax.detach()[0])\n```\n\n\n![png](README_files/README_6_0.png)\n\n\n\n```python\n# Compute scoring and enumeration (forward / inside)\nlog_partition = dist.partition\nmax_score = dist.log_prob(dist.argmax)\n```\n\n\n```python\n# Compute samples \nshow(dist.sample((1,)).detach()[0, 0])\n```\n\n\n![png](README_files/README_8_0.png)\n\n\n\n```python\n# Padding/Masking built into library.\ndist = DependencyCRF(vals, lengths=torch.tensor([10, 7]))\nshow(dist.marginals[0])\nplt.show()\nshow(dist.marginals[1])\n```\n\n\n![png](README_files/README_9_0.png)\n\n\n\n![png](README_files/README_9_1.png)\n\n\n\n```python\n# Many other structured prediction approaches\nchain = torch.zeros(2, 10, 10, 10) + 1e-5\nchain[:, :, :, :] = vals.unsqueeze(-1).exp()\nchain[:, :, :, :] += torch.eye(10, 10).view(1, 1, 10, 10) \nchain[:, 0, :, 0] = 1\nchain[:, -1,9, :] = 1\nchain = chain.log()\n\ndist = LinearChainCRF(chain)\nshow(dist.marginals.detach()[0].sum(-1))\n```\n\n\n![png](README_files/README_10_0.png)\n\n\n## Library\n\nFull docs: http://nlp.seas.harvard.edu/pytorch-struct/\n\nCurrent distributions implemented:\n\n* LinearChainCRF \n* SemiMarkovCRF \n* DependencyCRF \n* NonProjectiveDependencyCRF\n* TreeCRF \n* NeuralPCFG / NeuralHMM\n\nEach distribution includes: \n\n* Argmax, sampling, entropy, partition, masking, log_probs, k-max\n\nExtensions:\n\n* Integration with `torchtext`, `pytorch-transformers`, `dgl`\n* Adapters for generative structured models (CFG / HMM / HSMM)\n* Common tree structured parameterizations TreeLSTM / SpanLSTM\n\n\n## Low-level API: \n\nEverything implemented through semiring dynamic programming. \n\n* Log Marginals\n* Max and MAP computation\n* Sampling through specialized backprop\n* Entropy and first-order semirings. \n\n\n## Examples\n\n* BERT \u003ca href=\"https://github.com/harvardnlp/pytorch-struct/blob/master/notebooks/BertTagger.ipynb\"\u003ePart-of-Speech\u003c/a\u003e \n* BERT \u003ca href=\"https://github.com/harvardnlp/pytorch-struct/blob/master/notebooks/BertDependencies.ipynb\"\u003eDependency Parsing\u003c/a\u003e\n* \u003ca href=\"https://github.com/harvardnlp/pytorch-struct/blob/master/notebooks/Unsupervised_CFG.ipynb\"\u003eUnsupervised Learning\u003c/a\u003e \n* \u003ca href=\"https://github.com/harvardnlp/pytorch-struct/blob/master/examples/tree.py\"\u003eStructured VAE \u003c/a\u003e\n\n\u003cimg src=\"https://media.giphy.com/media/IdxKpsWBHa5PpjuhHM/giphy.gif\"\u003e\n\n\n\n## Citation\n\n```\n@misc{alex2020torchstruct,\n    title={Torch-Struct: Deep Structured Prediction Library},\n    author={Alexander M. Rush},\n    year={2020},\n    eprint={2002.00876},\n    archivePrefix={arXiv},\n    primaryClass={cs.CL}\n}\n```\n\nThis work was partially supported by NSF grant IIS-1901030. \n","funding_links":[],"categories":["Jupyter Notebook","Pytorch \u0026 related libraries｜Pytorch \u0026 相关库","GitHub","Deep Learning Framework","Pytorch \u0026 related libraries","Pytorch实用程序"],"sub_categories":["NLP \u0026 Speech Processing｜自然语言处理 \u0026 语音处理:","High-Level DL APIs","NLP \u0026 Speech Processing:"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharvardnlp%2Fpytorch-struct","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fharvardnlp%2Fpytorch-struct","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharvardnlp%2Fpytorch-struct/lists"}