{"id":20679807,"url":"https://github.com/toshas/tbasis","last_synced_at":"2025-04-19T23:53:17.890Z","repository":{"id":132938508,"uuid":"385687772","full_name":"toshas/tbasis","owner":"toshas","description":"T-Basis: a Compact Representation for Neural Networks","archived":false,"fork":false,"pushed_at":"2021-07-13T17:45:11.000Z","size":1494,"stargazers_count":9,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-19T23:53:12.866Z","etag":null,"topics":["compression","icml","pytorch","reparameterization","reproducibility","reproducible-research","tensor","tensor-decomposition","tensor-ring","weight-sharing"],"latest_commit_sha":null,"homepage":"https://www.obukhov.ai/tbasis","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/toshas.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-07-13T17:41:36.000Z","updated_at":"2024-07-05T08:27:32.000Z","dependencies_parsed_at":null,"dependency_job_id":"3685a261-8910-4b42-8473-3d4a0ff45a19","html_url":"https://github.com/toshas/tbasis","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/toshas%2Ftbasis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/toshas%2Ftbasis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/toshas%2Ftbasis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/toshas%2Ftbasis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/toshas","download_url":"https://codeload.github.com/toshas/tbasis/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249830852,"owners_count":21331357,"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":["compression","icml","pytorch","reparameterization","reproducibility","reproducible-research","tensor","tensor-decomposition","tensor-ring","weight-sharing"],"created_at":"2024-11-16T21:27:43.335Z","updated_at":"2025-04-19T23:53:17.840Z","avatar_url":"https://github.com/toshas.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## T-Basis: a Compact Representation for Neural Networks \n\n\u003cimg src=\"doc/teaser.png\" align=\"left\" width=\"33%\"\u003e\n\nThis repository is the official implementation of our ICML 2020 paper titled \"T-Basis: a Compact Representation for \nNeural Networks\" \n[[arXiv]](https://arxiv.org/abs/2007.06631) \n[[PMLR]](http://proceedings.mlr.press/v119/obukhov20a.html). \n\nIt demonstrates how to perform low-rank neural network training in a compressed form. \nThe code provides select experiments (image classification and semantic segmentation) from the paper (see \n`configs/icml20` directory).\n\n## Installation and Datasets\n\nClone the repository, then create a new virtual environment, and install python dependencies into it:\n```bash\npython3 -m venv venv_tbasis\nsource venv_tbasis/bin/activate\npip3 install --upgrade pip\npip3 install -r requirements.txt\n```\n\nIn case of problems with generic requirements, fall back to \n[requirements_reproducibility.txt](doc/requirements_reproducibility.txt).\n\n## Logging\n\nThe code performs logging to the console, tensorboard file in the experiment log directory, and also Weights and Biases \n(wandb). Upon the first run, please enter your wandb credentials, which can be obtained by registering a free account \nwith the service.\n\n## Creating Environment Config\n\nThe training script allows specifying multiple `yml` config files, which will be concatenated during execution. \nThis is done to separate experiment configs from environment configs. \nTo start running experiments, create your own config file with a few environment settings, similar to \n[configs/env_lsf.yml](configs/env_lsf.yml). Generally, you only need to update paths; see other fields explained in \n[config reference](doc/config.md).\n\n## Training\n\nChoose a preconfigured experiment from any of the `configs/icml20/*` directories, or compose your own config \nusing the [config reference](doc/config.md), and run the following command:\n\n```shell\nCUDA_VISIBLE_DEVICES=0 python -m src.train --cfg configs/env_yours.yml --cfg configs/experiment.yml\n```\n\n## Citation\n\nPlease cite our work if you found it useful:\n\n```\n@InProceedings{obukhov2020tbasis,\n  title={T-Basis: a Compact Representation for Neural Networks},\n  author={Obukhov, Anton and Rakhuba, Maxim and Georgoulis, Stamatios and Kanakis, Menelaos and Dai, Dengxin and Van Gool, Luc},\n  booktitle={Proceedings of the 37th International Conference on Machine Learning},\n  pages={7392--7404},\n  year={2020},\n  editor={Hal Daumé III and Aarti Singh},\n  volume={119},\n  series={Proceedings of Machine Learning Research},\n  month={13--18 Jul},\n  publisher={PMLR},\n  pdf={http://proceedings.mlr.press/v119/obukhov20a/obukhov20a.pdf},\n  url={http://proceedings.mlr.press/v119/obukhov20a.html}\n}\n```\n\n## License\nThis software is released under a CC-BY-NC 4.0 license, which allows personal and research use only. For a commercial \nlicense, please contact the authors. You can view a license summary here.\n\nPortions of source code taken from external sources are annotated with links to original files and their corresponding \nlicenses.\n\n## Acknowledgements\nThis work was supported by Toyota Motor Europe and was carried out at the TRACE Lab at ETH Zurich (Toyota Research on \nAutomated Cars in Europe - Zurich).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftoshas%2Ftbasis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftoshas%2Ftbasis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftoshas%2Ftbasis/lists"}