{"id":13935560,"url":"https://github.com/fehimornek/DeepForSpeed","last_synced_at":"2025-07-19T20:33:12.183Z","repository":{"id":62330525,"uuid":"446198732","full_name":"fehimornek/DeepForSpeed","owner":"fehimornek","description":"ConvNet learns to play Need For Speed","archived":false,"fork":false,"pushed_at":"2022-03-19T10:07:20.000Z","size":4024,"stargazers_count":248,"open_issues_count":0,"forks_count":27,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-11-08T07:03:27.645Z","etag":null,"topics":["convolutional-neural-networks","deep-learning","neural-network","self-driving-car"],"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/fehimornek.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-01-09T20:45:07.000Z","updated_at":"2024-11-07T11:54:25.000Z","dependencies_parsed_at":"2022-10-30T22:45:28.889Z","dependency_job_id":null,"html_url":"https://github.com/fehimornek/DeepForSpeed","commit_stats":null,"previous_names":["fehimornek/deepforspeed","edilgin/deepforspeed"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fehimornek%2FDeepForSpeed","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fehimornek%2FDeepForSpeed/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fehimornek%2FDeepForSpeed/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fehimornek%2FDeepForSpeed/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fehimornek","download_url":"https://codeload.github.com/fehimornek/DeepForSpeed/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226677098,"owners_count":17666002,"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":["convolutional-neural-networks","deep-learning","neural-network","self-driving-car"],"created_at":"2024-08-07T23:01:52.765Z","updated_at":"2024-11-27T03:30:48.043Z","avatar_url":"https://github.com/fehimornek.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# DeepForSpeed: Data Wanted\n## A self-driving car in Need For Speed\nThe inspiration comes from how Nvidia built a self-driving car with just a single convolutional\nneural network instead of many fancy algorithms combined. Here my goal is to replicate \nthe amazing results they've gotten but inside a game. But i also tried to create it as a platform/interface \nin which different architectures can be tested relatively easily, so it can also be used as a benchmark.\nSo it's like a fun driving simulator (of course not an accurate one) that you can test your own neural networks \nat and maybe conduct some experiments.\n\n## Watch The Latest Version\n[![Watch the video](https://img.youtube.com/vi/t0iqfM36mRc/maxresdefault.jpg)](https://youtu.be/t0iqfM36mRc)\nnote: this is a cherry picked example and many times model will not perform this well. Im hoping to change that in future versions.\n\n## Things used\n\u003e Python 3.9\n\u003e \n\u003e Pytorch 1.10\n\u003e\n\u003e Numpy\n\u003e \n\u003e OpenCV\n\u003e \n\u003e Matplotlib\n\u003e \n\u003e Need For Speed: Most Wanted 2005\n\u003e \n\u003e Base architecture\n\u003e \n\u003e \u003cimg src=\"https://github.com/edilgin/DeepForSpeed/blob/master/images/nvidia_arch.png?raw=true\" width=40% height=40% alt=\"Nvidia's architecture\"\u003e\n\n\n## How to use it\nThere is different ways to use it depending on what you want. Additional info can be found inside the scripts.\n\n\nCreating and processing data\n\n\u003cimg src=\"https://github.com/edilgin/DeepForSpeed/blob/master/images/dataFlowchart.jpg?raw=true\" width=50% height=50% alt=\"flowchart\"\u003e\n\nUsing models\n\n\u003cimg src=\"https://github.com/edilgin/DeepForSpeed/blob/master/images/trainFlowchart.jpg?raw=true\" width=50% height=50% alt=\"flowchart\"\u003e\n\n\n## Pull requests\nTLDR: Basically any improvements are really appreciated.\n\n- Other Neural Network architectures\n- Refinements in the code\n- Trained Models\n- Anything you can get done on future updates part\n\n\n\n## For Future Updates:\n- Add tensorflow board\n- Only use np arrays instead of both lists and np arrays in data\n- RGB images instead of gray images\n- Train on more data\n- Increase data resolution\n- Controller or a steering wheel to get the input\n- Different activation functions\n- Try Weight Decay\n- Add merging data function for easing data creation\n- Save models whilst training\n\n### References:\npaper by nvidia: https://images.nvidia.com/content/tegra/automotive/images/2016/solutions/pdf/end-to-end-dl-using-px.pdf\n\nSentdex's PyGta5 playlist: https://www.youtube.com/watch?v=ks4MPfMq8aQ\u0026list=PLQVvvaa0QuDeETZEOy4VdocT7TOjfSA8a\n\nNFS:MW mods are taken from:  https://github.com/ExOptsTeam/NFSMWExOpts\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffehimornek%2FDeepForSpeed","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffehimornek%2FDeepForSpeed","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffehimornek%2FDeepForSpeed/lists"}