{"id":13994483,"url":"https://github.com/mead-ml/mead-baseline","last_synced_at":"2025-04-06T12:11:00.508Z","repository":{"id":39787865,"uuid":"56975673","full_name":"mead-ml/mead-baseline","owner":"mead-ml","description":"Deep-Learning Model Exploration and Development for NLP","archived":false,"fork":false,"pushed_at":"2023-10-13T19:42:21.000Z","size":11710,"stargazers_count":243,"open_issues_count":13,"forks_count":73,"subscribers_count":20,"default_branch":"master","last_synced_at":"2025-03-30T11:07:20.931Z","etag":null,"topics":["baseline","bert","classification","convolutional-neural-networks","deep-learning","deep-learning-architectures","experimentation","hacktoberfest","keras","language-model","machine-learning","nlp","nlp-tasks","pytorch","recurrent-neural-networks","seq2seq","tensorflow","transformers","visdom"],"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/mead-ml.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":"2016-04-24T14:23:02.000Z","updated_at":"2025-01-21T04:00:37.000Z","dependencies_parsed_at":"2023-12-15T21:17:44.682Z","dependency_job_id":"6001aa15-20d4-4e71-a728-bc92ca5f4ad9","html_url":"https://github.com/mead-ml/mead-baseline","commit_stats":{"total_commits":2086,"total_committers":16,"mean_commits":130.375,"dds":"0.23921380632790024","last_synced_commit":"5d7632bb151c2d09501ebf49f36ba8c4204df4c8"},"previous_names":["dpressel/baseline","dpressel/mead-baseline"],"tags_count":10,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mead-ml%2Fmead-baseline","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mead-ml%2Fmead-baseline/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mead-ml%2Fmead-baseline/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mead-ml%2Fmead-baseline/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mead-ml","download_url":"https://codeload.github.com/mead-ml/mead-baseline/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247478324,"owners_count":20945266,"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":["baseline","bert","classification","convolutional-neural-networks","deep-learning","deep-learning-architectures","experimentation","hacktoberfest","keras","language-model","machine-learning","nlp","nlp-tasks","pytorch","recurrent-neural-networks","seq2seq","tensorflow","transformers","visdom"],"created_at":"2024-08-09T14:02:53.864Z","updated_at":"2025-04-06T12:11:00.481Z","avatar_url":"https://github.com/mead-ml.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# MEAD\n\nMEAD is a library for reproducible deep learning research and fast model\ndevelopment for NLP. It provides easily extensible abstractions and\nimplementations for data loading, model development, training, experiment tracking and export to production. \n\nIt also provides implementations of high-performance deep learning models for various NLP tasks, against which newly developed models\ncan be compared. Deep learning experiments are hard to reproduce, MEAD\nprovides functionalities to track them. The goal is to allow a researcher to\nfocus on model development, delegating the repetitive tasks to the library.\n\n[Documentation](https://github.com/dpressel/mead-baseline/blob/master/docs/main.md)\n\n[Tutorials using Colab](https://github.com/dpressel/mead-tutorials)\n\n[MEAD Hub](https://github.com/mead-ml/hub)\n\n## Installation\n\n### Pip\n\nBaseline can be installed as a Python package.\n\n`pip install mead-baseline`\n\nYou will need to have\n`tensorflow_addons` already installed or have it get installed directly with: \n\n`pip install mead-baseline[tf2]`\n\n### From the repository\n\nIf you have a clone of this repostory and want to install from it:\n\n```\ncd layers\npip install -e .\ncd ../\npip install -e .\n```\n\nThis first installs `mead-layers` AKA 8 mile, a tiny layers API containing PyTorch and TensorFlow primitives, locally and then `mead-baseline`\n\n### Dockerhub\n\nWe use Github CI/CD to automatically release TensorFlow and PyTorch via this project:\n\nhttps://github.com/mead-ml/mead-gpu\n\nLinks to the latest dockerhub images can be found there\n\n## A Note About Versions\n\nDeep Learning Frameworks are evolving quickly and changes are not always\nbackwards compatible. We recommend recent versions of whichever framework is being used underneath.  We currently test on TF versions 2.1.0 and 2.4.1.\nThe PyTorch backend requires at least version 1.3.0, though we recommend using a more recent version.\n\n## Citing\n\nIf you use the library, please cite the following paper:\n\n```\n@InProceedings{W18-2506,\n  author =    \"Pressel, Daniel\n               and Ray Choudhury, Sagnik\n               and Lester, Brian\n               and Zhao, Yanjie\n               and Barta, Matt\",\n  title =     \"Baseline: A Library for Rapid Modeling, Experimentation and\n               Development of Deep Learning Algorithms targeting NLP\",\n  booktitle = \"Proceedings of Workshop for NLP Open Source Software (NLP-OSS)\",\n  year =      \"2018\",\n  publisher = \"Association for Computational Linguistics\",\n  pages =     \"34--40\",\n  location =  \"Melbourne, Australia\",\n  url =       \"http://aclweb.org/anthology/W18-2506\"\n}\n```\n\nMEAD was selected for a Spotlight Poster at the NeurIPS MLOSS workshop in 2018.  [OpenReview link](https://openreview.net/forum?id=r1xEb7J15Q)\n\n### Acknowledgements\n\n- Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmead-ml%2Fmead-baseline","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmead-ml%2Fmead-baseline","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmead-ml%2Fmead-baseline/lists"}