{"id":15432749,"url":"https://github.com/gugarosa/dropout_rbm","last_synced_at":"2025-03-18T11:42:23.870Z","repository":{"id":98631725,"uuid":"350024220","full_name":"gugarosa/dropout_rbm","owner":"gugarosa","description":"📄 Official implementation regarding the paper \"Fine-Tuning Dropout Regularization in Energy-Based Deep Learning\". ","archived":false,"fork":false,"pushed_at":"2022-10-06T12:59:03.000Z","size":17,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-18T07:39:50.650Z","etag":null,"topics":["dropout","fine-tuning","implementation","paper","rbm"],"latest_commit_sha":null,"homepage":"","language":"Python","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/gugarosa.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":"2021-03-21T14:34:47.000Z","updated_at":"2022-07-22T13:59:21.000Z","dependencies_parsed_at":"2023-03-07T10:30:42.027Z","dependency_job_id":null,"html_url":"https://github.com/gugarosa/dropout_rbm","commit_stats":{"total_commits":8,"total_committers":1,"mean_commits":8.0,"dds":0.0,"last_synced_commit":"aee5b243fbe5016689b6d1473cd555270638ba22"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gugarosa%2Fdropout_rbm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gugarosa%2Fdropout_rbm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gugarosa%2Fdropout_rbm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gugarosa%2Fdropout_rbm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gugarosa","download_url":"https://codeload.github.com/gugarosa/dropout_rbm/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244216807,"owners_count":20417651,"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":["dropout","fine-tuning","implementation","paper","rbm"],"created_at":"2024-10-01T18:28:29.529Z","updated_at":"2025-03-18T11:42:23.844Z","avatar_url":"https://github.com/gugarosa.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Fine-Tuning Dropout Regularization in Energy-Based Deep Learning\n\n*This repository holds all the necessary code to run the very-same experiments described in the paper \"Fine-Tuning Dropout Regularization in Energy-Based Deep Learning\".*\n\n---\n\n## References\n\nIf you use our work to fulfill any of your needs, please cite us:\n\n```BibTex\n@inproceedings{deRosa:21,\n  author={de Rosa, Gustavo H. and Roder, Mateus and Papa, Jo{\\~a}o P.},\n  editor={Tavares, Jo{\\~a}o Manuel R. S. and Papa, Jo{\\~a}o Paulo and Gonz{\\'a}lez Hidalgo, Manuel},\n  title={Fine-Tuning Dropout Regularization in Energy-Based Deep Learning},\n  booktitle={Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications},\n  year={2021},\n  publisher={Springer International Publishing},\n  address={Cham},\n  pages={99--108},\n  isbn={978-3-030-93420-0}\n}\n```\n\n---\n\n## Structure\n\n * `models`: Holds the output history and models files.\n * `utils`\n   * `loader.py`: Utility to load datasets and split them into training, validation and testing sets;\n   * `objects.py`: Wraps objects instantiation for command line usage;\n   * `opt.py`: Wraps the optimization pipeline;\n   * `target.py`: Wraps the optimization target.\n   \n   \n---\n\n## Package Guidelines\n\n### Installation\n\nInstall all the pre-needed requirements using:\n\n```Python\npip install -r requirements.txt\n```\n\n*If you encounter any problems with the automatic installation of the [learnergy](https://github.com/gugarosa/learnergy) package, contact us.*\n\n### Data configuration\n\nIn order to run the experiments, you can use `torchvision` to load pre-implemented datasets.\n\n---\n\n## Usage\n\n### Model Optimization\n\nThe experiment is conducted by optimizating an architecture and post-evaluating them. To accomplish such a step, one needs to use the following script:\n\n```Python\npython optimization.py -h\n```\n\n*Note that `-h` invokes the script helper, which assists users in employing the appropriate parameters.*\n\n### Test Reconstruction\n\nAfterward, with the optimized Dropout parameter in hands, one can perform the final reconstruction over the testing test, as follows:\n\n```Python\npython test_reconstruction.py -h\n```\n\n### Bash Script\n\nInstead of invoking every script to conduct the experiments, it is also possible to use the provided shell script, as follows:\n\n```Bash\n./pipeline.sh\n```\n\nSuch a script will conduct every step needed to accomplish the experimentation used throughout this paper. Furthermore, one can change any input argument that is defined in the script.\n\n---\n\n## Support\n\nWe know that we do our best, but it is inevitable to acknowledge that we make mistakes. If you ever need to report a bug, report a problem, talk to us, please do so! We will be available at our bests at this repository.\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgugarosa%2Fdropout_rbm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgugarosa%2Fdropout_rbm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgugarosa%2Fdropout_rbm/lists"}