{"id":21367561,"url":"https://github.com/aggrathon/trafficsignrecognizer","last_synced_at":"2026-04-13T17:32:25.625Z","repository":{"id":101402781,"uuid":"97643501","full_name":"Aggrathon/TrafficSignRecognizer","owner":"Aggrathon","description":"A neural network for recognizing traffic signs in images","archived":false,"fork":false,"pushed_at":"2021-10-09T10:04:16.000Z","size":9555,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-06-15T20:06:10.072Z","etag":null,"topics":["ai","android","android-app","machine-learning","neural-network","python","python3","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Aggrathon.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-07-18T21:01:01.000Z","updated_at":"2021-10-09T10:04:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"75293dda-56f6-4755-9b08-473612c93117","html_url":"https://github.com/Aggrathon/TrafficSignRecognizer","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/Aggrathon/TrafficSignRecognizer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aggrathon%2FTrafficSignRecognizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aggrathon%2FTrafficSignRecognizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aggrathon%2FTrafficSignRecognizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aggrathon%2FTrafficSignRecognizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Aggrathon","download_url":"https://codeload.github.com/Aggrathon/TrafficSignRecognizer/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Aggrathon%2FTrafficSignRecognizer/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269201157,"owners_count":24377448,"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","status":"online","status_checked_at":"2025-08-07T02:00:09.698Z","response_time":73,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["ai","android","android-app","machine-learning","neural-network","python","python3","tensorflow"],"created_at":"2024-11-22T07:19:41.450Z","updated_at":"2026-04-13T17:32:20.597Z","avatar_url":"https://github.com/Aggrathon.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TrafficSignRecognizer\nA neural network for recognizing traffic signs in images.\nThe network is used in an Android app for recording images through the windscreen of a car and remembering the last sign.\nEven though that it is function, do not use it while driving since it is mostly a distraction from the road.\n\n## App\nThe Android app can be downloaded [here](https://github.com/Aggrathon/TrafficSignRecognizer/releases).  \nWhen evaluated on the training material it reached a precision of 99.6%.\nSince it was trained on roughly 30 000 images this accuracy doesn't seem to be due to overfitting.\nIn practise it has difficulties with tunnels and anything not recorded from a road but is otherwise pretty accurate.\nSince it is only trained on Finnish signs, your experience may vary.\n\n\n## Neural Network\nThe `data` folder contains some scipt for easily sort through source material and prepare it for learning.  \nUse `train.py` to train the network and `export.py` to prepare the trained model for use in the app.\nIn the `model.py` is the layout of the network defined and it looks like this:\n\n| Convolution 1 | Convolution 2 | Convolution 3 | Fully Connected 1 | Fully Connected 2 | Prediction |\n| ------------- | ------------- | ------------- | ----------------- | ----------------- | ---------- |\n| Size: 32      | Size: 48      | Size: 64      | Size: 256         | Size: 64          | Size: 1    |\n| Conv2d ReLU   | Conv2d ReLU   | Conv2d ReLU   | ReLU              | ReLU              | Sigmoid    |\n| Max Pooling   | Max Pooling   | Max Pooling   | Dropout           | Dropout           |            |\n| Normalization | Normalization | Normalization |                   |                   |            |\n\n\n## Dependencies\n- Python 3\n- Tensorflow\n- Pygame (for source material sorting)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faggrathon%2Ftrafficsignrecognizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faggrathon%2Ftrafficsignrecognizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faggrathon%2Ftrafficsignrecognizer/lists"}