{"id":13737696,"url":"https://github.com/YU1ut/MixMatch-pytorch","last_synced_at":"2025-05-08T15:30:53.635Z","repository":{"id":36612502,"uuid":"187955577","full_name":"YU1ut/MixMatch-pytorch","owner":"YU1ut","description":"Code for \"MixMatch - A Holistic Approach to Semi-Supervised Learning\"","archived":false,"fork":false,"pushed_at":"2023-11-02T15:46:45.000Z","size":21,"stargazers_count":630,"open_issues_count":27,"forks_count":129,"subscribers_count":12,"default_branch":"master","last_synced_at":"2024-08-04T03:11:07.051Z","etag":null,"topics":["deep-learning","pytorch","semi-supervised-learning"],"latest_commit_sha":null,"homepage":null,"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/YU1ut.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}},"created_at":"2019-05-22T03:22:19.000Z","updated_at":"2024-07-30T03:26:23.000Z","dependencies_parsed_at":"2022-09-05T03:01:25.816Z","dependency_job_id":"70134cb2-1fad-44f4-b318-5dc808813ebf","html_url":"https://github.com/YU1ut/MixMatch-pytorch","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/YU1ut%2FMixMatch-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YU1ut%2FMixMatch-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YU1ut%2FMixMatch-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YU1ut%2FMixMatch-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YU1ut","download_url":"https://codeload.github.com/YU1ut/MixMatch-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224742232,"owners_count":17362229,"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":["deep-learning","pytorch","semi-supervised-learning"],"created_at":"2024-08-03T03:01:57.632Z","updated_at":"2024-11-15T06:30:48.094Z","avatar_url":"https://github.com/YU1ut.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# MixMatch\nThis is an unofficial PyTorch implementation of [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://arxiv.org/abs/1905.02249). \nThe official Tensorflow implementation is [here](https://github.com/google-research/mixmatch).\n\nNow only experiments on CIFAR-10 are available.\n\nThis repository carefully implemented important details of the official implementation to reproduce the results.\n\n\n## Requirements\n- Python 3.6+\n- PyTorch 1.0\n- **torchvision 0.2.2 (older versions are not compatible with this code)** \n- tensorboardX\n- progress\n- matplotlib\n- numpy\n\n## Usage\n\n### Train\nTrain the model by 250 labeled data of CIFAR-10 dataset:\n\n```\npython train.py --gpu \u003cgpu_id\u003e --n-labeled 250 --out cifar10@250\n```\n\nTrain the model by 4000 labeled data of CIFAR-10 dataset:\n\n```\npython train.py --gpu \u003cgpu_id\u003e --n-labeled 4000 --out cifar10@4000\n```\n\n### Monitoring training progress\n```\ntensorboard.sh --port 6006 --logdir cifar10@250\n```\n\n## Results (Accuracy)\n| #Labels | 250 | 500 | 1000 | 2000| 4000 |\n|:---|:---:|:---:|:---:|:---:|:---:|\n|Paper | 88.92 ± 0.87 | 90.35 ± 0.94 | 92.25 ± 0.32| 92.97 ± 0.15 |93.76 ± 0.06|\n|This code | 88.71 | 88.96 | 90.52 | 92.23 | 93.52 |\n\n(Results of this code were evaluated on 1 run. Results of 5 runs with different seeds will be updated later. )\n\n## References\n```\n@article{berthelot2019mixmatch,\n  title={MixMatch: A Holistic Approach to Semi-Supervised Learning},\n  author={Berthelot, David and Carlini, Nicholas and Goodfellow, Ian and Papernot, Nicolas and Oliver, Avital and Raffel, Colin},\n  journal={arXiv preprint arXiv:1905.02249},\n  year={2019}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYU1ut%2FMixMatch-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYU1ut%2FMixMatch-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYU1ut%2FMixMatch-pytorch/lists"}