{"id":20519689,"url":"https://github.com/zongxr/industrial-algorithm-competition","last_synced_at":"2025-04-14T02:10:47.158Z","repository":{"id":112122032,"uuid":"418405580","full_name":"ZongXR/Industrial-Algorithm-Competition","owner":"ZongXR","description":"全国工业大数据算法大赛，省赛二等奖解决方案，已经过实际生产线验证。包括视觉检测模型和动态误差补偿模型。","archived":false,"fork":false,"pushed_at":"2021-12-20T07:19:19.000Z","size":20467,"stargazers_count":20,"open_issues_count":1,"forks_count":7,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-27T16:09:29.130Z","etag":null,"topics":["cv","docker","machinelearning","python","tensorflow"],"latest_commit_sha":null,"homepage":"","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/ZongXR.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}},"created_at":"2021-10-18T08:12:06.000Z","updated_at":"2025-01-24T09:46:18.000Z","dependencies_parsed_at":"2023-07-31T22:47:16.519Z","dependency_job_id":null,"html_url":"https://github.com/ZongXR/Industrial-Algorithm-Competition","commit_stats":null,"previous_names":["zongxr/industrial-algorithm-competition"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZongXR%2FIndustrial-Algorithm-Competition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZongXR%2FIndustrial-Algorithm-Competition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZongXR%2FIndustrial-Algorithm-Competition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZongXR%2FIndustrial-Algorithm-Competition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ZongXR","download_url":"https://codeload.github.com/ZongXR/Industrial-Algorithm-Competition/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248809046,"owners_count":21164896,"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":["cv","docker","machinelearning","python","tensorflow"],"created_at":"2024-11-15T22:15:43.698Z","updated_at":"2025-04-14T02:10:47.122Z","avatar_url":"https://github.com/ZongXR.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1\u003eIndustrial-Algorithm-Competition\u003c/h1\u003e\n全国工业大数据算法竞赛\n\u003ch2\u003e更新日志\u003c/h2\u003e\n\u003ctable\u003e\n\u003ctr\u003e\n\u003cth\u003e版本号\u003c/th\u003e\u003cth\u003e更新日期\u003c/th\u003e\u003cth\u003e更新内容\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e0.1.0.0\u003c/td\u003e\u003ctd\u003e2021年10月18日\u003c/td\u003e\u003ctd\u003e新增视觉检测模型\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e0.1.1.0\u003c/td\u003e\u003ctd\u003e2021年10月18日\u003c/td\u003e\u003ctd\u003e视觉检测pipeline模型去掉边缘检测;\u003cbr /\u003e提升视觉检测准确率\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e0.1.2.0\u003c/td\u003e\u003ctd\u003e2021年10月18日\u003c/td\u003e\u003ctd\u003e新增误差补偿模型\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e0.1.3.0\u003c/td\u003e\u003ctd\u003e2021年10月18日\u003c/td\u003e\u003ctd\u003e视觉检测模型同时输出两个类的预测概率\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e0.1.3.1\u003c/td\u003e\u003ctd\u003e2021年10月19日\u003c/td\u003e\u003ctd\u003e添加了一些说明\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e0.1.3.2\u003c/td\u003e\u003ctd\u003e2021年10月19日\u003c/td\u003e\u003ctd\u003e修复BUG\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e0.1.4.0\u003c/td\u003e\u003ctd\u003e2021年10月20日\u003c/td\u003e\u003ctd\u003e现在可以同时部署多个模型\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\u003ch2\u003e项目经验\u003c/h2\u003e\n\u003col\u003e\n\u003cli\u003e在分类问题中，如果loss还在下降，而accuracy保持不变，那么不要着急，多训练几轮accuracy就上来了\u003c/li\u003e\n\u003c/ol\u003e\n\u003ch2\u003e任务描述\u003c/h2\u003e\n\u003ch3\u003e分类任务\u003c/h3\u003e\n\u003cb\u003e合格品不合格品检测\u003c/b\u003e\u003cbr /\u003e\n\u003cb\u003e合格品\u003c/b\u003e\n\u003cimg src=\"data/pic/train/0/616bb0a2ac4eb86ec92bf933.png\" alt=\"合格品\" /\u003e\u003cbr /\u003e\n\u003cb\u003e不合格品\u003c/b\u003e\n\u003cimg src=\"data/pic/train/1/616bb88cac4eb86ec92bfa67.png\" alt=\"不合格品\" /\u003e\u003cbr /\u003e\n\u003ca href=\"http://81.70.8.71:8501/v1/models/pic_clf:predict\" target=\"_blank\"\u003e向此地址发送POST请求\u003c/a\u003e\n\u003ctable\u003e\n\u003ctr\u003e\n\u003cth\u003e请求参数\u003c/th\u003e\u003cth\u003e含义\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003einstances\u003c/td\u003e\u003ctd\u003e4维张量转成的数组\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\u003ch3\u003e回归任务\u003c/h3\u003e\n\u003cb\u003e动态误差实时补偿\u003c/b\u003e\u003cbr /\u003e\n\u003ca href=\"http://81.70.8.71:8501/v1/models/adjustment:predict\" target=\"_blank\"\u003e向此地址发送POST请求\u003c/a\u003e\n\u003ctable\u003e\n\u003ctr\u003e\n\u003cth\u003e请求参数\u003c/th\u003e\u003cth\u003e含义\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003einstances\u003c/td\u003e\u003ctd\u003e2维张量转成的数组\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzongxr%2Findustrial-algorithm-competition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzongxr%2Findustrial-algorithm-competition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzongxr%2Findustrial-algorithm-competition/lists"}