{"id":20245096,"url":"https://github.com/bestburning/mhxy","last_synced_at":"2025-04-09T18:17:32.408Z","repository":{"id":40607897,"uuid":"248462070","full_name":"BestBurning/mhxy","owner":"BestBurning","description":"tensorflow实践：梦幻西游人物弹窗识别","archived":false,"fork":false,"pushed_at":"2020-03-21T12:18:32.000Z","size":19549,"stargazers_count":260,"open_issues_count":2,"forks_count":120,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-04-09T18:17:25.977Z","etag":null,"topics":["kmclass","opencv","python","tensorflow","tensorflow2"],"latest_commit_sha":null,"homepage":"https://di1shuai.com/tags/#%E6%A2%A6%E5%B9%BB%E8%A5%BF%E6%B8%B8","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BestBurning.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}},"created_at":"2020-03-19T09:31:21.000Z","updated_at":"2025-04-01T15:16:42.000Z","dependencies_parsed_at":"2022-08-10T03:12:05.371Z","dependency_job_id":null,"html_url":"https://github.com/BestBurning/mhxy","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BestBurning%2Fmhxy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BestBurning%2Fmhxy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BestBurning%2Fmhxy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BestBurning%2Fmhxy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BestBurning","download_url":"https://codeload.github.com/BestBurning/mhxy/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248085321,"owners_count":21045139,"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":["kmclass","opencv","python","tensorflow","tensorflow2"],"created_at":"2024-11-14T09:18:56.078Z","updated_at":"2025-04-09T18:17:32.388Z","avatar_url":"https://github.com/BestBurning.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# mhxy\ntensorflow实践：梦幻西游人物弹窗识别\n\n## 环境描述\n[Windows](https://www.microsoft.com/zh-cn/software-download/windows10)\n\n```\nC:\\Users\\SF\u003ever\nMicrosoft Windows [版本 10.0.18363.720]\n```\n\n[Python](https://www.python.org/downloads/)\n```\nC:\\Users\\SF\u003epython --version\nPython 3.7.6\n```\n\n[Tensorflow](https://www.tensorflow.org/install)\n```\nC:\\Users\\SF\u003epython\nPython 3.7.6 (tags/v3.7.6:43364a7ae0, Dec 19 2019, 00:42:30) [MSC v.1916 64 bit (AMD64)] on win32\nType \"help\", \"copyright\", \"credits\" or \"license\" for more information.\n\u003e\u003e\u003e import tensorflow as tf\n2020-03-19 23:42:50.170828: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll\n\u003e\u003e\u003e tf.__version__\n'2.1.0'\n```\n\n[CUDA](https://developer.nvidia.com/cuda-downloads)\n```\nC:\\Users\\SF\u003envcc --version\nnvcc: NVIDIA (R) Cuda compiler driver\nCopyright (c) 2005-2019 NVIDIA Corporation\nBuilt on Wed_Oct_23_19:32:27_Pacific_Daylight_Time_2019\nCuda compilation tools, release 10.2, V10.2.89\n\n```\n\n[cuDNN](https://developer.nvidia.com/cudnn)\n```\nC:\\tools\\cuda\\include\\cudnn.h\n\n...\n#define CUDNN_MAJOR 7\n\n#define CUDNN_MINOR 6\n#define CUDNN_PATCHLEVEL 5\n#define CUDNN_VERSION (CUDNN_MAJOR * 1000 + CUDNN_MINOR * 100 + CUDNN_PATCHLEVEL)\n...\n```\n\n[梦幻西游](http://xyq.163.com/download/index.html?=xyqload)\n```\n启动方式   多标签版\n分辨率     800x600\n界面风格   暖风\n\n```\n![](https://github.com/BestBurning/mhxy/blob/master/images/github/mhxy_setting_1.jpg)\n![](https://github.com/BestBurning/mhxy/blob/master/images/github/mhxy_setting_2.jpg)\n\n\n## 运行\n\n由于**鼠标点击**使用了[kmclassdll](https://github.com/BestBurning/kmclassdll)，所以需要开启 **测试模式** \u0026 **禁用强制驱动签名** 并 **重启**\n\n`管理员身份`打开`CMD`\n```\nbcdedit /set nointegritychecks on\n\nbcdedit /set testsigning on\n\nshutdown  -r -t 0\n```\n重启后，`管理员身份`打开`CMD`\n\n- 自动点击弹窗\n```\npython main.py --click 0\n```\n\n- 持续学习\n```\npython main.py --learn 0\n```\n如果使用`学习`功能的话，请下载[训练库](https://github.com/BestBurning/mhxy/releases)\n更多代码解读可以参考[这里](https://di1shuai.com/tags/%E6%A2%A6%E5%B9%BB%E8%A5%BF%E6%B8%B8/)\n\n\n## 成果展示\n\n![](https://github.com/BestBurning/mhxy/blob/master/images/github/result.gif)\n\n可以看到一次预测点击的耗时是在**4s**左右，欢迎**Star**\n\n## 目录说明\n\n- [driver](https://github.com/BestBurning/mhxy/blob/master/driver)  --  [kmclass键鼠驱动](https://github.com/BestBurning/kmclass)文件夹\n\n- [images](https://github.com/BestBurning/mhxy/blob/master/images)  --  截图文件夹\n  - [flag](https://github.com/BestBurning/mhxy/blob/master/images/flag)   -- 标识文件夹：战斗标识、鼠标标识、弹框标识 \n  - [github](https://github.com/BestBurning/mhxy/blob/master/images/github)  -- github文件夹 \n- [model](https://github.com/BestBurning/mhxy/blob/master/model)  --  tensorflow 模型文件夹\n\n## 文件说明\n\n- [auto_click.bat](https://github.com/BestBurning/mhxy/blob/master/auto_click.bat)   \n运行弹框识别并点击的脚本\n\n- [auto.py](https://github.com/BestBurning/mhxy/blob/master/auto.py)          \n键鼠的包装\n\n- [constant.py](https://github.com/BestBurning/mhxy/blob/master/constant.py)      \n常量定义\n\n- [data_model.py](https://github.com/BestBurning/mhxy/blob/master/data_model.py)    \n模型训练、读取、预测\n\n- [keymouse.py](https://github.com/BestBurning/mhxy/blob/master/keymouse.py)      \n[kmclassdll](https://github.com/BestBurning/kmclassdll) 键鼠动态库调用\n\n- [learn_clean.py](https://github.com/BestBurning/mhxy/blob/master/learn_clean.py)   \n学习并清除学过的文件的脚本\n\n- [main.py](https://github.com/BestBurning/mhxy/blob/master/main.py)          \n程序入口\n\n- [screen.py](https://github.com/BestBurning/mhxy/blob/master/screen.py)      \n屏幕截图、图片处理相关\n\n- [util.py](https://github.com/BestBurning/mhxy/blob/master/util.py)          \n工具类  \n\n## 声明\n\n本人无任何商业目的，仅用于学习和娱乐，[源代码](https://github.com/BestBurning/mhxy)采用了[AGPL3.0](https://opensource.org/licenses/AGPL-3.0)开源协议","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbestburning%2Fmhxy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbestburning%2Fmhxy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbestburning%2Fmhxy/lists"}