{"id":13689464,"url":"https://github.com/bearpaw/pytorch-classification","last_synced_at":"2025-05-15T10:08:00.367Z","repository":{"id":43612160,"uuid":"90824610","full_name":"bearpaw/pytorch-classification","owner":"bearpaw","description":"Classification with PyTorch.","archived":false,"fork":false,"pushed_at":"2024-06-18T02:36:02.000Z","size":438,"stargazers_count":1725,"open_issues_count":34,"forks_count":558,"subscribers_count":29,"default_branch":"master","last_synced_at":"2025-04-11T19:59:49.094Z","etag":null,"topics":["cifar10","cifar100","classification","densenet","imagenet","preresnet","pytorch","resnet","resnext","wide-residual-networks","wrn"],"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/bearpaw.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":"2017-05-10T05:33:36.000Z","updated_at":"2025-04-07T08:32:14.000Z","dependencies_parsed_at":"2024-10-14T20:20:29.687Z","dependency_job_id":"b53b912a-9e41-4dba-82aa-3c495943ddfb","html_url":"https://github.com/bearpaw/pytorch-classification","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/bearpaw%2Fpytorch-classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bearpaw%2Fpytorch-classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bearpaw%2Fpytorch-classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bearpaw%2Fpytorch-classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bearpaw","download_url":"https://codeload.github.com/bearpaw/pytorch-classification/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254319721,"owners_count":22051074,"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":["cifar10","cifar100","classification","densenet","imagenet","preresnet","pytorch","resnet","resnext","wide-residual-networks","wrn"],"created_at":"2024-08-02T15:01:48.894Z","updated_at":"2025-05-15T10:07:55.347Z","avatar_url":"https://github.com/bearpaw.png","language":"Python","readme":"# pytorch-classification\nClassification on CIFAR-10/100 and ImageNet with PyTorch.\n\n## Features\n* Unified interface for different network architectures\n* Multi-GPU support\n* Training progress bar with rich info\n* Training log and training curve visualization code (see `./utils/logger.py`)\n\n## Install\n* Install [PyTorch](http://pytorch.org/)\n* Clone recursively\n  ```\n  git clone --recursive https://github.com/bearpaw/pytorch-classification.git\n  ```\n\n## Training\nPlease see the [Training recipes](TRAINING.md) for how to train the models.\n\n## Results\n\n### CIFAR\nTop1 error rate on the CIFAR-10/100 benchmarks are reported. You may get different results when training your models with different random seed.\nNote that the number of parameters are computed on the CIFAR-10 dataset.\n\n| Model                     | Params (M)         |  CIFAR-10 (%)      | CIFAR-100 (%)      |\n| -------------------       | ------------------ | ------------------ | ------------------ |\n| alexnet                   | 2.47               | 22.78              | 56.13              |\n| vgg19_bn                  | 20.04              | 6.66               | 28.05              |\n| ResNet-110                | 1.70               | 6.11               | 28.86              |\n| PreResNet-110             | 1.70               | 4.94               | 23.65              |\n| WRN-28-10 (drop 0.3)      | 36.48              | 3.79               | 18.14              |\n| ResNeXt-29, 8x64          | 34.43              | 3.69               | 17.38              |\n| ResNeXt-29, 16x64         | 68.16              | 3.53               | 17.30              |\n| DenseNet-BC (L=100, k=12) | 0.77               | 4.54               | 22.88              |\n| DenseNet-BC (L=190, k=40) | 25.62              | 3.32               | 17.17              |\n\n\n![cifar](utils/images/cifar.png)\n\n### ImageNet\nSingle-crop (224x224) validation error rate is reported. \n\n\n| Model                | Params (M)         |  Top-1 Error (%)   | Top-5 Error  (%)   |\n| -------------------  | ------------------ | ------------------ | ------------------ |\n| ResNet-18            | 11.69              |  30.09             | 10.78              |\n| ResNeXt-50 (32x4d)   | 25.03              |  22.6              | 6.29               |\n\n![Validation curve](utils/images/imagenet.png)\n\n## Pretrained models\nOur trained models and training logs are downloadable at [OneDrive](https://mycuhk-my.sharepoint.com/personal/1155056070_link_cuhk_edu_hk/_layouts/15/guestaccess.aspx?folderid=0a380d1fece1443f0a2831b761df31905\u0026authkey=Ac5yBC-FSE4oUJZ2Lsx7I5c).\n\n## Supported Architectures\n\n### CIFAR-10 / CIFAR-100\nSince the size of images in CIFAR dataset is `32x32`, popular network structures for ImageNet need some modifications to adapt this input size. The modified models is in the package `models.cifar`:\n- [x] [AlexNet](https://arxiv.org/abs/1404.5997)\n- [x] [VGG](https://arxiv.org/abs/1409.1556) (Imported from [pytorch-cifar](https://github.com/kuangliu/pytorch-cifar))\n- [x] [ResNet](https://arxiv.org/abs/1512.03385)\n- [x] [Pre-act-ResNet](https://arxiv.org/abs/1603.05027)\n- [x] [ResNeXt](https://arxiv.org/abs/1611.05431) (Imported from [ResNeXt.pytorch](https://github.com/prlz77/ResNeXt.pytorch))\n- [x] [Wide Residual Networks](http://arxiv.org/abs/1605.07146) (Imported from [WideResNet-pytorch](https://github.com/xternalz/WideResNet-pytorch))\n- [x] [DenseNet](https://arxiv.org/abs/1608.06993)\n\n### ImageNet\n- [x] All models in `torchvision.models` (alexnet, vgg, resnet, densenet, inception_v3, squeezenet)\n- [x] [ResNeXt](https://arxiv.org/abs/1611.05431)\n- [ ] [Wide Residual Networks](http://arxiv.org/abs/1605.07146)\n\n\n## Contribute\nFeel free to create a pull request if you find any bugs or you want to contribute (e.g., more datasets and more network structures).\n","funding_links":[],"categories":["Tutorials \u0026 books \u0026 examples｜教程 \u0026 书籍 \u0026 示例","Python","Tutorials, books, \u0026 examples"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbearpaw%2Fpytorch-classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbearpaw%2Fpytorch-classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbearpaw%2Fpytorch-classification/lists"}