{"id":24293545,"url":"https://github.com/jizongfox/deep-clustering-toolbox","last_synced_at":"2025-06-23T04:36:20.827Z","repository":{"id":52703004,"uuid":"183987331","full_name":"jizongFox/deep-clustering-toolbox","owner":"jizongFox","description":"PyTorch Vision Toolbox not only for deep-clustering","archived":false,"fork":false,"pushed_at":"2022-10-21T15:58:57.000Z","size":322844,"stargazers_count":29,"open_issues_count":18,"forks_count":4,"subscribers_count":6,"default_branch":"master_dev","last_synced_at":"2024-10-11T09:23:21.349Z","etag":null,"topics":["clustering","framework","pytorch","segmentation","semi-supervised-learning","toolbox"],"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/jizongFox.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":"2019-04-29T02:37:09.000Z","updated_at":"2024-02-05T09:42:27.000Z","dependencies_parsed_at":"2022-08-21T19:00:15.507Z","dependency_job_id":null,"html_url":"https://github.com/jizongFox/deep-clustering-toolbox","commit_stats":null,"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jizongFox%2Fdeep-clustering-toolbox","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jizongFox%2Fdeep-clustering-toolbox/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jizongFox%2Fdeep-clustering-toolbox/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jizongFox%2Fdeep-clustering-toolbox/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jizongFox","download_url":"https://codeload.github.com/jizongFox/deep-clustering-toolbox/tar.gz/refs/heads/master_dev","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234232356,"owners_count":18800085,"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":["clustering","framework","pytorch","segmentation","semi-supervised-learning","toolbox"],"created_at":"2025-01-16T16:29:47.781Z","updated_at":"2025-01-16T16:29:51.733Z","avatar_url":"https://github.com/jizongFox.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# deep-clustering-toolbox\n#### PyTorch Vision toolbox not only for deep-clustering\n### Introduction\nI still use this repo for research propose. I update some modules frequently to make the framework flexible enough.\n\nThis repo contains the base code for a deep learning framework using `PyTorch`, to benchmark algorithms for various dataset.\nThe current version supports `MNIST`, `CIFAR10`, `SVHN` and `STL-10` for semisupervised and unsupervised learning.\n`ACDC`, `Promise12`, `WMH` and so on are supported as segmentation counterpart.\n\n#### Features:\n\u003e- Powerful cmd parser using `yaml` module, providing flexible input formats without predefined argparser.\n\u003e- Automatic checkpoint management adapting to various settings\n\u003e- Automatic meter recording and experimental status plotting using matplotlib and threads\n\u003e- Various build-in loss functions and help tricks and assert statements frequently used in PyTorch Framework, such as `disable_tracking_bn`, `ema`, `vat`, etc.\n\u003e- Various post-processing tools such as Viewer for Medical image segmentations, multislice_viwers for 3D dataset real-time debug\nand report script for experimental summaries.\n\u003e- Extendable modules for rapid development.\n\n#### Several projects are benefited from this scalable framework, builing top on this, including:\n\n+ DeepClustering implemented for\n\u003e- `Invariant Information Clustering for Unsupervised Image Classification and Segmentation`,\n\u003e- `Learning Discrete Representations via Information Maximizing Self-Augmented Training`,\n\u003e- [`Information based Deep Clustering: An experimental study`](https://github.com/jizongFox/DeepClusteringProject)\n+ SemiSupervised classification for\n\u003e- `Semi-Supervised Learning by Augmented Distribution Alignment`,\n\u003e- `Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning`,\n\u003e- `Temporal Ensembling for Semi-Supervised Learning`,\n\u003e- `Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results`\n+ SemiSupervised Segmentation for\n\u003e- `Adversarial Learning for Semi-Supervised Semantic Segmentation`,\n\u003e- `Semi-Supervised and Task-Driven Data Augmentation`,\n\u003e- [`Deep Co-Training for Semi-Supervised Image Segmentation`](https://arxiv.org/abs/1903.11233)\n+ Discretely-constrained CNN for\n\u003e- [`Discretely-constrained deep network for weakly-supervised segmentation`](https://github.com/jizongFox/Discretly-constrained-CNN/),  \n\u003e- `Mutual information based segmentation on medical imaging`\n\n\nThey are examples how to develop research framework with the assistance of our proposed `deep-clustering-toolbox`.\n___\n### Playground\n\nSeveral papers have been implemented based on this framework. I store them in the `playground` folder. The papers include:\n\n\u003e- [`Auto-Encoding Variational Bayes`](https://arxiv.org/abs/1312.6114)\n\u003e- [`mixup: BEYOND EMPIRICAL RISK MINIMIZATION`](https://arxiv.org/pdf/1710.09412.pdf)\n\u003e- [`MINE: Mutual Information Neural Estimation`](https://arxiv.org/abs/1801.04062)\n\u003e- [`Averaging Weights Leads to Wider Optima and Better Generalization`](https://arxiv.org/pdf/1803.05407.pdf)\n\u003e- [`THERE ARE MANY CONSISTENT EXPLANATIONS OF UNLABELED DATA: WHY YOU SHOULD AVERAGE`](https://arxiv.org/pdf/1806.05594.pdf)\n\u003e- [`Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation`](https://arxiv.org/abs/1904.06346)\n\n\n---\n### Installation\n```bash\ngit clone https://github.com/jizongFox/deep-clustering-toolbox.git\ncd deep-clustering-toolbox  \npython setup install # for those who do not want to make changes immediately.\n# or\npython setup develop # for those who want to modify the code and make the impact immediate.\n\n```\nOr very simply\n```bash\npip install deepclustering\n```\n### Citation\nIf you feel useful for your project, please consider citing this work.\n```latex\n@article{peng2019deep,\n  title={Deep Co-Training for Semi-Supervised Image Segmentation},\n  author={Peng, Jizong and Estradab, Guillermo and Pedersoli, Marco and Desrosiers, Christian},\n  journal={arXiv preprint arXiv:1903.11233},\n  year={2019}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjizongfox%2Fdeep-clustering-toolbox","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjizongfox%2Fdeep-clustering-toolbox","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjizongfox%2Fdeep-clustering-toolbox/lists"}