{"id":15944548,"url":"https://github.com/yannickfunk/streestsignrecognition","last_synced_at":"2026-06-05T19:32:02.498Z","repository":{"id":110685596,"uuid":"211736544","full_name":"yannickfunk/streestsignrecognition","owner":"yannickfunk","description":"Street Sign Recognition for Autonomous Driving","archived":false,"fork":false,"pushed_at":"2019-09-29T22:59:32.000Z","size":17,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-06T01:47:36.177Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/yannickfunk.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":"2019-09-29T22:55:53.000Z","updated_at":"2020-08-31T20:50:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"cb9820e7-ed73-4bbc-b2bb-3a72fcf7afe8","html_url":"https://github.com/yannickfunk/streestsignrecognition","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/yannickfunk/streestsignrecognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yannickfunk%2Fstreestsignrecognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yannickfunk%2Fstreestsignrecognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yannickfunk%2Fstreestsignrecognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yannickfunk%2Fstreestsignrecognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yannickfunk","download_url":"https://codeload.github.com/yannickfunk/streestsignrecognition/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yannickfunk%2Fstreestsignrecognition/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33957498,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-05T02:00:06.157Z","response_time":120,"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":[],"created_at":"2024-10-07T08:41:17.957Z","updated_at":"2026-06-05T19:32:02.478Z","avatar_url":"https://github.com/yannickfunk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Traffic Sign Recognition\n\n#### Description\n\nIn this project I built a 97% accurate classifier for street sign recognition. I used the large German Traffic Sign Recognition Benchmark data set https://www.kaggle.com/meowmeowmeowmeowmeow/gtsrb-german-traffic-sign which contains over 40 classes for training a convolutional neural network.\n\n#### Training Results\n\nAfter training 800 epochs using 30% of the data for validation, I obtained a validation accuracy of 97%.\n\nThe following confusion matrix shows the predictions of the network:\n\n![alt text](confusion_matrix.PNG)\n\nAs seen, the classifier is very robust, due to nearly zero entries on the side diagonals.\n\nThe classification report:\n\n\n\n \tprecision recall f1-score support\n 0 1.00 1.00 1.00 84\n 1 0.98 0.96 0.97 888\n 2 1.00 1.00 1.00 804\n 3 0.98 0.99 0.99 528\n 4 0.98 1.00 0.99 840\n 5 1.00 1.00 1.00 864\n 6 0.97 1.00 0.99 312\n 7 0.96 0.96 0.96 252\n 8 0.99 0.99 0.99 168\n 9 1.00 1.00 1.00 444\n 10 0.96 1.00 0.98 480\n 11 1.00 0.94 0.97 84\n 12 0.99 0.97 0.98 900\n 13 0.91 0.96 0.93 144\n 14 0.96 0.99 0.98 132\n 15 0.97 1.00 0.98 156\n 16 0.99 0.93 0.96 204\n 17 0.96 0.98 0.97 108\n 18 0.99 0.95 0.97 600\n 19 0.99 0.93 0.96 240\n 20 0.99 1.00 0.99 96\n 21 0.93 1.00 0.96 216\n 22 0.76 0.74 0.75 108\n 23 0.99 1.00 0.99 564\n 24 1.00 0.87 0.93 180\n 25 0.98 1.00 0.99 312\n 26 1.00 0.69 0.81 96\n 27 0.88 0.92 0.90 275\n 28 0.80 0.81 0.80 168\n 29 0.99 1.00 0.99 480\n 30 0.95 0.88 0.92 156\n 31 0.79 0.65 0.71 84\n 32 0.91 0.96 0.93 828\n 33 0.80 0.58 0.67 120\n 34 0.99 0.99 0.99 792\n 35 0.82 0.97 0.89 144\n 36 1.00 1.00 1.00 96\n 37 0.99 1.00 0.99 96\n 38 0.97 0.97 0.97 744\n 39 1.00 0.98 0.99 168\n 40 0.96 0.97 0.96 576\n 41 0.96 0.99 0.98 564\n 42 0.99 1.00 1.00 588\n \n accuracy 0.97 15683\n macro avg 0.95 0.94 0.95 15683\n weighted avg 0.97 0.97 0.97 15683\nshows that there are some classes, not recognized well (e.g 31), but this correlates directly with the lack of training data supporting this class. Except for the underrepresented classes, the prediction values are very good.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyannickfunk%2Fstreestsignrecognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyannickfunk%2Fstreestsignrecognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyannickfunk%2Fstreestsignrecognition/lists"}