{"id":13488657,"url":"https://github.com/Prinsphield/Wechat_AutoJump","last_synced_at":"2025-03-28T01:36:56.212Z","repository":{"id":141906083,"uuid":"115782836","full_name":"Prinsphield/Wechat_AutoJump","owner":"Prinsphield","description":"AI plays WeChat Jump Game","archived":false,"fork":false,"pushed_at":"2019-11-21T17:37:39.000Z","size":931,"stargazers_count":1278,"open_issues_count":14,"forks_count":412,"subscribers_count":69,"default_branch":"master","last_synced_at":"2024-10-30T00:33:28.693Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://zhuanlan.zhihu.com/p/32636329","language":"Python","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/Prinsphield.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":"2017-12-30T08:01:19.000Z","updated_at":"2024-10-22T00:45:27.000Z","dependencies_parsed_at":null,"dependency_job_id":"2f49e7c3-3007-46f5-85f9-f5a664ac67c8","html_url":"https://github.com/Prinsphield/Wechat_AutoJump","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/Prinsphield%2FWechat_AutoJump","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Prinsphield%2FWechat_AutoJump/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Prinsphield%2FWechat_AutoJump/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Prinsphield%2FWechat_AutoJump/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Prinsphield","download_url":"https://codeload.github.com/Prinsphield/Wechat_AutoJump/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222333976,"owners_count":16968058,"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":"2024-07-31T18:01:19.629Z","updated_at":"2024-10-31T00:32:14.713Z","avatar_url":"https://github.com/Prinsphield.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# 自动玩微信小游戏跳一跳\n\n中文说明请点[这里](https://github.com/Prinsphield/Wechat_AutoJump/blob/master/readme_cn.md)\n\n## Requirements\n\n- Python\n- Opencv3\n- Tensorflow\n\n#### for Android\n\n- Adb tools\n- Android Phone\n\n#### for IOS (Refer to this [site](https://testerhome.com/topics/7220) for installation)\n\n- iPhone\n- Mac\n- WebDriverAgent\n- facebook-wda\n- imobiledevice\n\n## Algorithms for Localization\n\n- Multiscale search\n- Fast search\n- CNN-based coarse-to-fine model\n\nFor algorithm details, please go to [https://zhuanlan.zhihu.com/p/32636329](https://zhuanlan.zhihu.com/p/32636329).\n\n**Notice: CV based fast-search only support Android for now**\n\n## Run\n\nBefore running our code, connect to your phone via USB.\n\nIf Android phone, open the USB debugging at developer options enter `adb devices` to ensure that the list is not empty.\nIf iPhone, please ensure that you have a mac. Then following this [link](https://testerhome.com/topics/7220) for preparation.\n\nIt is **recommended** to download the pre-trained model following the link below and run the following code\n\n\tpython nn_play.py --phone Android --sensitivity 2.045\n\nYou can also try `play.py` by running the following code\n\n\tpython play.py --phone Android --sensitivity 2.045\n\n- `--phone` has two options: Android or IOS.\n- `--sensitivity` is the constant parameter that controls the pressing time.\n- `nn_play.py` uses CNN-based coarse-to-fine model, supporting Android and IOS (more robust)\n- `play.py` uses multiscale search and fast search algorithms, supporting Android and IOS (it may fail sometimes in other phones)\n\n## Performance\n\nOur method can correctly detect the positions of the man (green dot) and the destination (red dot).\n\nIt is easy to reach the state of art as long as you like.\nBut I choose to go die after 859 jumps for about 1.5 hours.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg align=\"center\" src=\"resource/state_859.png\" width=\"250\" alt=\"state_859\"\u003e\n\u003cimg align=\"center\" src=\"resource/state_859_res.png\" width=\"250\" alt=\"state_859\"\u003e\n\u003cimg align=\"center\" src=\"resource/sota.png\" width=\"250\" alt=\"sota\"\u003e\n\u003c/div\u003e\n\u003cbr/\u003e\n\n## Demo Video\n\nHere is a video demo. Excited!\n\n[![微信跳一跳](https://img.youtube.com/vi/OeTI2Kx8Ehc/0.jpg)](https://youtu.be/OeTI2Kx8Ehc \"自动玩微信小游戏跳一跳\")\n\n## Train Log \u0026 Data\n\nCNN train log and train\u0026validation data avaliable at\n- [Baidu Drive](https://pan.baidu.com/s/1c2rrlra)\n- [Google Drive](https://drive.google.com/drive/folders/1tCUf2krzMpkQh_RJL02x0z__4j7MaUI4?usp=sharing)\n\n**Training:** download and untar data into any directory, and then modify `self.data_dir` in those files under `cnn_coarse_to_fine/data_provider` directory.\n\n**Inference:** download and unzip train log dirs(`train_logs_coarse` and `train_logs_fine`) into `resource` directory.\n\n## How to Train CNN models by yourself?\n\n0. Download and untar data into any directory, and then modify `self.data_dir` in those files under `cnn_coarse_to_fine/data_provider` directory.\n0. `base.large` is model dir for coarse model, `base.fine` is model dir for fine model, other dirs under `cnn_coarse_to_fine/config` are models we don't use, but if you have interests, you can try train other models by yourself.\n0. Run `python3 train.py -g 0` to train your model, `-g` to specify GPU to use, if you don't have GPU, training model is not recommended because training speed with CPU is very slow.\n0. After training, move or copy `.ckpt` file to train log dirs(`train_logs_coarse` and `train_logs_fine`) for use.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FPrinsphield%2FWechat_AutoJump","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FPrinsphield%2FWechat_AutoJump","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FPrinsphield%2FWechat_AutoJump/lists"}