{"id":18694466,"url":"https://github.com/luickk/gta_self_driving","last_synced_at":"2025-04-12T07:11:05.015Z","repository":{"id":122825229,"uuid":"102459838","full_name":"luickk/gta_self_driving","owner":"luickk","description":"CNN that is trained to drive vehicles in GTAV","archived":false,"fork":false,"pushed_at":"2023-08-30T10:12:09.000Z","size":24904,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-10T20:25:23.596Z","etag":null,"topics":["gta5","python36","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/luickk.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2017-09-05T09:09:05.000Z","updated_at":"2023-08-30T09:56:11.000Z","dependencies_parsed_at":null,"dependency_job_id":"9b024454-9543-421f-a25a-eee2a79a381c","html_url":"https://github.com/luickk/gta_self_driving","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/luickk%2Fgta_self_driving","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luickk%2Fgta_self_driving/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luickk%2Fgta_self_driving/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/luickk%2Fgta_self_driving/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/luickk","download_url":"https://codeload.github.com/luickk/gta_self_driving/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248530575,"owners_count":21119600,"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":["gta5","python36","tensorflow"],"created_at":"2024-11-07T11:10:55.678Z","updated_at":"2025-04-12T07:11:04.998Z","avatar_url":"https://github.com/luickk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"GTA self driving Agent\n===================\n\nThe goal is to program a self-driving agent, that is capable of driving a car in gtaIV.\nSince the project aims on a approach which excludes every other data source except for the view of the driver the car is only ment to drive down a car way with no complex turning or overhaul maneuvers.\n\nDemonstration video can be watched [here](media/demo.mp4)\n\n----------\n\nRealization\n-------------\n\nThe Agent is programmed in python and trained with a [CNN](https://www.tensorflow.org/tutorials/wide_and_deep) which is based on [TensorFlow](https://www.tensorflow.org/).\n\n#### \u003ci class=\"icon-down-big\"\u003e\u003c/i\u003e Installation\n\n\t\u003e - Clone Repository\n\t\u003e - Install Dependencies\n\n#### \u003ci class=\"icon-camera\"\u003e\u003c/i\u003e Capture data\n\n\tTo collect data use collect_data.py.\n\tGta window has to be shrunk down to a resolution of 800x600\n\tand moved to the left upper corner.\n\t\n\tSet path variable to your prefered location.\n\tFiles will be saved in approximately 300KB .npy files(uncompressed).\n\t\n\tTo start collect_data.py several arguments can be used.\n\t\u003e - -s can be a number to define starting step manualy or \"forward\" to \n\tuse existing files as step indicator.\n\n#### \u003ci class=\"icon-ccw\"\u003e\u003c/i\u003e Training\n\n\tTo train your model use train.py.\n\tSet path variable to location where training data is saved.\n\tName your model by setting MODEL_NAME variable to your most preferred name.\n\t\n#### \u003ci class=\"icon-right-big\"\u003e\u003c/i\u003e Testing\n\n\tTo test your model use test_model.py.\n\tChoose your already trained model by setting MODEL_NAME variable to your best trained one.\n\t\n\tTo test the agent the Gta window has to be shrunk down to a resolution of 800x600\n\tand moved to the left upper corner.\n\t\n\tNow, everything is ready to be tested.\n\n#### \u003ci class=\"icon-archive\"\u003e\u003c/i\u003e Prefabricated models\n\n\tPrefabricated models will be provided as far as I can produce them myself and \n\tas far as they fit my own requirements.\n\n\nDependencies\n-------------------\n\n\u003e - numpy\n\u003e - TensorFlow\n\u003e - tflearn\n\u003e - cv2\n\u003e - sys\n\u003e - glob\n\u003e - optparse\n\u003e - threading\n\u003e - keyboard\n\u003e - win32gui, win32ui, win32con, win32api \u003cbr\u003e\n\u003e  If you get this error: `ImportError: DLL load failed: The specified module could not be found.`,\n\u003e  move *pythoncom36.dll* and *pywintypes36.dll* from \n\u003e  `Python36\\Lib\\site-packages\\pywin32_system32` to \n\u003e  `Python36\\Lib\\site-packages\\win32` \u003cbr\u003e\n\u003e  If you get this error: `ImportError: No module named win32gui`, after installing win32 and you are using 64 bit python install 64 bit win32 wheel from http://www.lfd.uci.edu/~gohlke/pythonlibs/#pywin32 by using `pip install \u003cname\u003e.whl`\n\u003e - re\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fluickk%2Fgta_self_driving","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fluickk%2Fgta_self_driving","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fluickk%2Fgta_self_driving/lists"}