{"id":18753697,"url":"https://github.com/baiyuetribe/ncnn-models","last_synced_at":"2025-04-09T10:08:24.927Z","repository":{"id":38322666,"uuid":"494294418","full_name":"Baiyuetribe/ncnn-models","owner":"Baiyuetribe","description":"awesome AI models with NCNN, and how they were converted ✨✨✨","archived":false,"fork":false,"pushed_at":"2023-07-07T15:32:23.000Z","size":156912,"stargazers_count":268,"open_issues_count":16,"forks_count":31,"subscribers_count":9,"default_branch":"main","last_synced_at":"2025-04-02T08:13:27.194Z","etag":null,"topics":["deep-learning","gfpgan","image-classification","nanodet","ncnn","ncnn-model","pytorch","rife","yolov5","yolov7","yolox"],"latest_commit_sha":null,"homepage":"https://github.com/Baiyuetribe/ncnn-models","language":"C++","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/Baiyuetribe.png","metadata":{"files":{"readme":"README-CN.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":"2022-05-20T02:28:29.000Z","updated_at":"2025-03-25T05:22:22.000Z","dependencies_parsed_at":"2024-01-14T12:17:59.449Z","dependency_job_id":"5e6702b4-ba06-4aea-8dcb-a1040982d30a","html_url":"https://github.com/Baiyuetribe/ncnn-models","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Baiyuetribe%2Fncnn-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Baiyuetribe%2Fncnn-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Baiyuetribe%2Fncnn-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Baiyuetribe%2Fncnn-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Baiyuetribe","download_url":"https://codeload.github.com/Baiyuetribe/ncnn-models/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248018060,"owners_count":21034048,"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","gfpgan","image-classification","nanodet","ncnn","ncnn-model","pytorch","rife","yolov5","yolov7","yolox"],"created_at":"2024-11-07T17:26:47.624Z","updated_at":"2025-04-09T10:08:24.906Z","avatar_url":"https://github.com/Baiyuetribe.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"##  \u003cp align=\"center\"\u003e ncnn models \u003c/p\u003e\n\nThe collection of pre-trained AI models, and how they were converted, deployed.\n\n![](docs/images/logo.png)\n\n### 关于\n\nncnn框架借助vulkan实现了全平台部署，我们通过pytorch、tensorflow、飞桨等预训练模型，然后转换成ncnn通用模型，实现Windows、mac、linux、安卓、ios、WebAssembly 以及uni-app的最终部署。然而模型转换并不是一键的，需要手动处理。为了拓展ncnn的边界应用，我们建立此仓库，欢迎提交接收任何转换成功或失败的案例。\n\n### 如何参与贡献？\n\nfork代码，然后按照如下格式提交，最好是c++20 的最小demo，不要内嵌并发。\n\nyolov5  # 项目名称\n- models/xx.bin or xx.param # model\n- input.png # 输入\n- out.png # 输出\n- README.md # 模型推理介绍、转换步骤、相关案例\n- convert.py # 从pytorch等模型转换具体复现代码\n\n灵感来自[ailia](https://github.com/axinc-ai/ailia-models),鉴于接收失败案例为主，因此失败案例优先排序，成功案例分类排序。\n\n### 一些代表\n\n- [nihui](https://github.com/nihui) ncnn作者\n- [飞哥](https://github.com/feigechuanshu) ncnn安卓系列\n- [EdVince](https://github.com/EdVince) ncnn自然语言系列\n- [baiyue](https://github.com/Baiyuetribe/paper2gui) ncnn在PC桌面GUI系列\n- [670***@qq.com](https://ext.dcloud.net.cn/plugin?id=5243) ncnn在uni-app中的应用\n- [nihui](https://github.com/nihui/ncnn_on_esp32) ncnn在嵌入式设备上的应用\n- [nihui](https://github.com/nihui/ncnn-webassembly-yolov5) ncnn在wasm实现案例\n\n### 跨设备的意义\n\n\u003e 维护一次代码，多设备可用。\n\n- 借助vulkan，无需繁重的cuda驱动\n- 借助wasm实现任意设备的模型部署\n- 借助uni-app可绕过java实现多端部署","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbaiyuetribe%2Fncnn-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbaiyuetribe%2Fncnn-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbaiyuetribe%2Fncnn-models/lists"}