{"id":25020618,"url":"https://github.com/stillmisty/cifar-10","last_synced_at":"2025-03-30T10:25:40.183Z","repository":{"id":267616897,"uuid":"901809635","full_name":"StillMisty/CIFAR-10","owner":"StillMisty","description":"仅使用Numpy对CIFAR-10训练CNN","archived":false,"fork":false,"pushed_at":"2024-12-11T11:12:31.000Z","size":46,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-05T12:16:45.728Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/StillMisty.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":"2024-12-11T11:02:21.000Z","updated_at":"2024-12-11T11:12:35.000Z","dependencies_parsed_at":"2024-12-11T12:32:59.208Z","dependency_job_id":null,"html_url":"https://github.com/StillMisty/CIFAR-10","commit_stats":null,"previous_names":["stillmisty/cifar-10"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/StillMisty%2FCIFAR-10","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/StillMisty%2FCIFAR-10/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/StillMisty%2FCIFAR-10/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/StillMisty%2FCIFAR-10/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/StillMisty","download_url":"https://codeload.github.com/StillMisty/CIFAR-10/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246304194,"owners_count":20755861,"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":[],"created_at":"2025-02-05T12:16:49.775Z","updated_at":"2025-03-30T10:25:40.157Z","avatar_url":"https://github.com/StillMisty.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CUFAR-10数据集训练\r\n\r\n## 环境管理\r\n\r\n本项目使用UV进行环境管理，具体使用方法如下：\r\n\r\n```shell\r\n# 安装UV（Windows环境）\r\npowershell -c \"irm https://astral.sh/uv/install.ps1 | iex\"\r\n\r\n# 同步环境\r\nuv sync\r\n```\r\n\r\n## 训练代码\r\n\r\ntrain_simple_convent.py是一个简单的卷积神经网络训练代码\r\n\r\ntrain_self_deep_convent.py是一个更深的卷积神经网络训练代码,具体结构如下：\r\n\r\n- 3个卷积层,每层后接ReLU激活和池化层\r\n- 2个全连接层,中间有ReLU激活\r\n- 使用Softmax进行最终分类\r\n- 权重使用He初始化方法\r\n- Z-score标准化\r\n\r\ntrain_self_deep_convent_L2.py相对于train_self_deep_convent.py使用了L2正则化，以及添加了Dropout层\r\n\r\n训练过程中会自动检测数据集是否存在，如果不存在会自动下载，耐心等待即可\r\n\r\n## 训练结果\r\n\r\n所有最终的模型文件存储在result文件夹下\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstillmisty%2Fcifar-10","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fstillmisty%2Fcifar-10","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstillmisty%2Fcifar-10/lists"}