{"id":18378665,"url":"https://github.com/creatcodebuild/deep-learning-capstone","last_synced_at":"2025-09-19T04:31:50.005Z","repository":{"id":93996589,"uuid":"67643859","full_name":"CreatCodeBuild/deep-learning-capstone","owner":"CreatCodeBuild","description":"Deep Learning of Udacity's Machine Learning Capstone Project","archived":false,"fork":false,"pushed_at":"2016-10-04T03:43:08.000Z","size":7780,"stargazers_count":4,"open_issues_count":0,"forks_count":6,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-08T02:51:21.312Z","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/CreatCodeBuild.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":"2016-09-07T21:09:04.000Z","updated_at":"2020-07-28T01:47:57.000Z","dependencies_parsed_at":"2023-04-26T11:32:08.376Z","dependency_job_id":null,"html_url":"https://github.com/CreatCodeBuild/deep-learning-capstone","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CreatCodeBuild/deep-learning-capstone","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CreatCodeBuild%2Fdeep-learning-capstone","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CreatCodeBuild%2Fdeep-learning-capstone/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CreatCodeBuild%2Fdeep-learning-capstone/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CreatCodeBuild%2Fdeep-learning-capstone/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CreatCodeBuild","download_url":"https://codeload.github.com/CreatCodeBuild/deep-learning-capstone/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CreatCodeBuild%2Fdeep-learning-capstone/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":275881570,"owners_count":25545398,"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":"2025-09-19T02:00:09.700Z","response_time":108,"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":"2024-11-06T00:34:41.913Z","updated_at":"2025-09-19T04:31:49.372Z","avatar_url":"https://github.com/CreatCodeBuild.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# deep-learning-capstone\r\nDeep Learning Capstone Project for Udacity's Machine Learning Nanodegree\r\n\r\n# How to run it\r\nYou need tensorflow installed in your system to run it. TensorFlow only supports Linux and Mac right now.\r\n\r\nI used Python2 to write this project.\r\n\r\nOpen your terminal\r\n```\r\n# You need to create a ./data dir at your working dir when first time running it\r\npython dp.py\r\n```\r\nThis will run the default routine.\r\n\r\nYou can also specify the exact parameters to run. Create a new pytohn file\r\n```\r\nimport dp\r\nnet = dp.Net(\r\n\tnum_hidden=64,\r\n\tbatch_size=64,\r\n\tpatch_size=7,\r\n\tconv1_depth=16,\r\n\tconv2_depth=16,\r\n\tpooling_stride=2,\r\n\tdrop_out_rate=0.9,\r\n\tnum_steps=5001,\r\n\toptimizer='momentum',\r\n\tbase_learning_rate=0.0013,\r\n\tdecay_rate=0.99,\r\n\ttrain_csv='record/train.csv', test_csv='record/test.csv',\r\n\tmodel_name='model.ckpt'\r\n)\r\nnet.train()\r\nnet.test()\r\n```\r\nYou can of course just open dp.py and modify code directly in the secion\r\n```\r\nif __name__ == '__main__':\r\n    # Your code here\r\n```\r\nAfter you call net.train(), a model with your specified name will be created in ./data dir\r\n\r\nThen you can call net.test() to resotre the model without calling train() again.\r\n\r\n# Note\r\ngit ignores .mat files. Please download data sets from http://ufldl.stanford.edu/housenumbers/\r\n\r\nThen create data/ dir and put them in this dir\r\n\r\nYou need train_32x32.mat and test_32x32.mat\r\n\r\nReport is in report/report.pdf\r\n\r\nrecord/ contains all the result data\r\n\r\nchart/ contains all the charts\r\n\r\n\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcreatcodebuild%2Fdeep-learning-capstone","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcreatcodebuild%2Fdeep-learning-capstone","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcreatcodebuild%2Fdeep-learning-capstone/lists"}