{"id":19198345,"url":"https://github.com/deepvac/syszuxnsfw","last_synced_at":"2025-04-10T10:13:34.379Z","repository":{"id":113079965,"uuid":"283091770","full_name":"DeepVAC/SYSZUXnsfw","owner":"DeepVAC","description":"一个高质量的用于NSFW（涉黄检测等领域）的测试集","archived":false,"fork":false,"pushed_at":"2020-08-20T12:35:16.000Z","size":585,"stargazers_count":7,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-24T09:05:06.638Z","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":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DeepVAC.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":"2020-07-28T03:48:51.000Z","updated_at":"2025-02-21T13:00:35.000Z","dependencies_parsed_at":null,"dependency_job_id":"92021cf8-e569-40ed-b9e3-b5d723338357","html_url":"https://github.com/DeepVAC/SYSZUXnsfw","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/DeepVAC%2FSYSZUXnsfw","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepVAC%2FSYSZUXnsfw/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepVAC%2FSYSZUXnsfw/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepVAC%2FSYSZUXnsfw/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DeepVAC","download_url":"https://codeload.github.com/DeepVAC/SYSZUXnsfw/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248198889,"owners_count":21063628,"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":"2024-11-09T12:21:27.983Z","updated_at":"2025-04-10T10:13:34.360Z","avatar_url":"https://github.com/DeepVAC.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SYSZUXnsfw\n一个高质量的用于NSFW（涉黄检测等领域）的测试集          \n\nSYSZUXnsfw具有如下特点：\n\n- 划分为porn(涉黄)、 sexy(性感)、 neutral(中立)三部分，每部分300张测试图片；\n- 划分为标准：裸露敏感部位或者明显性行为判定为涉黄、穿着少裸露大面积皮肤但未暴露隐私部位判定为性感、其余为中立；                   \n- 贴近实际环境，分数高低直接体现算法落地的成熟度；             \n- 标准的ClassifierReport模块来打分，公平程度犹如高考；               \n\ndataset目录中的图片文件使用git lfs维护，克隆该项目前，你需要首先安装git-lfs：\n```bash\n#on Linux\napt install git-lfs\n\n#on macOS\nbrew install git-lfs\n```\n然后：\n```bash\n#克隆该项目\ngit clone https://github.com/DeepVAC/SYSZUXnsfw\n\n#拉取dataset图片\ngit lfs pull\n```\n\n## 使用说明\n\n项目的目录说明如下：     \n\n|  目录   |  说明   |  上传进度  |\n|---------|---------|------------|\n|dataset  |数据集   |\n|porn     |涉黄图片 |未上传      |\n|sexy     |性感图片 |更新20200730|\n|neutral  |中立图片 |更新20200730|\n|src      |测试示例代码|未上传   |\n\n\n## 如何计算分数\n\n测试集上的分数可以通过deepvac项目lib库的syszux_report模块（ClassifierReport类，来自https://github.com/DeepVAC/deepvac/blob/master/lib/syszux_report.py ）给出。ClassifierReport类会给三分类的混淆矩阵和评估指标。\n\n#### 混淆矩阵\n\n|      | 涉黄 | 性感 | 中立 |\n|------|------|------|------|\n| 涉黄 | 295  | 5    | 0    |\n| 性感 | 9    | 290  | 1    |\n| 中立 | 0    | 3    | 297  |\n   \n#### 混淆矩阵说明：\n- 第一行说明300张涉黄图片295张预测为涉黄即分类正确，5张预测为性感即分类错误，0张预测为中立；               \n- 第二行说明300张性感图片9张预测为涉黄即分类错误，290张预测为性感即分类正确，1张预测为中立即分类错误；               \n- 第一行说明300张中立图片0张预测为涉黄，3张预测为性感即分类错误，297张预测为中立即分类正确；               \n\n|    | 1   | 0   |\n|----|-----|-----|\n| 1  | TP  | FN  |\n| 0  | FP  | TN  |\n\n#### 评估指标\n预测正确样本数量(numcorrect)：(TP+TN)；              \n准确率(accuracy)：(TP+TN) / (TP+FN+FP+TN)；  \n每一类的精准率(precision)：FP / (TP+FP)；         \n每一类的召回率(precision)：FP / (TP+FN)；        \n每一类的F1-Score：F1-score = 2TP/(2TP+FP+FN)；     \n准确率accuracy和精确率precision都高的情况下，F1 score也会显得很高；          \n\n#### 使用ClassifierReport模块来进行以上分数的计算\n```python\n#use the ClassifierReport class\nreport = ClassifierReport('gemfield',5, 3)\nreport.add(1, 2).add(1, 1).add(0, 0).add(0, 2).add(2, 2)\nreport()\n```\n程序会输出markdown格式的报告：\n- dataset: gemfield\n- duration: 0.000\n- accuracy: 0.600\n\n- CONFUSION-MATRIX\n\n| gemfield | cls0 | cls1 | cls2 \n|---|---|---|---\n| cls0 | 1 | 0 | 1 \n| cls1 | 0 | 1 | 1 \n| cls2 | 0 | 0 | 1 \n\n- TEST NSFW REPORT\n\n| gemfield | cls0 | cls1 | cls2 \n|---|---|---|---\n| precision | 1.000 | 1.000 | 0.333 \n| recall | 0.500 | 0.500 | 1.000 \n| f1-score | 0.667 | 0.667 | 0.500 \n\n## 使用许可\n本项目仅限用于纯粹的学术研究，如：\n- 个人学习；\n- 比赛排名；\n- 公开发表且开源其实现的论文；\n\n不得用于任何形式的商业牟利，包括但不限于：\n- 任何形式的商业获利行为；\n- 任何形式的商务机会获取；\n- 任何形式的商业利益交换；\n\n\n## 项目贡献\n我们欢迎各种形式的贡献，包括但不限于：\n- 提交自己的作品/产品在SYSZUXnsfw上的成绩；\n- 发现和Fix项目的bug；\n- 提交高质量的测试集数据；\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepvac%2Fsyszuxnsfw","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeepvac%2Fsyszuxnsfw","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepvac%2Fsyszuxnsfw/lists"}