{"id":26728690,"url":"https://github.com/cserajdeep/dnn-iris-pytorch","last_synced_at":"2026-05-02T05:07:46.848Z","repository":{"id":165428909,"uuid":"380556480","full_name":"cserajdeep/DNN-IRIS-PyTorch","owner":"cserajdeep","description":"Deep Neural Network with Batch normalization for tabulat datasets.","archived":false,"fork":false,"pushed_at":"2021-06-26T19:41:38.000Z","size":164,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-18T12:51:51.589Z","etag":null,"topics":["batch","batch-normalization","classification","cuda","deep-learning","dnn","iris-dataset"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cserajdeep.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":"2021-06-26T17:11:45.000Z","updated_at":"2021-11-25T05:17:56.000Z","dependencies_parsed_at":"2024-07-14T03:15:06.775Z","dependency_job_id":null,"html_url":"https://github.com/cserajdeep/DNN-IRIS-PyTorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/cserajdeep/DNN-IRIS-PyTorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FDNN-IRIS-PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FDNN-IRIS-PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FDNN-IRIS-PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FDNN-IRIS-PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cserajdeep","download_url":"https://codeload.github.com/cserajdeep/DNN-IRIS-PyTorch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cserajdeep%2FDNN-IRIS-PyTorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32523474,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-02T01:12:54.858Z","status":"online","status_checked_at":"2026-05-02T02:00:05.923Z","response_time":132,"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":["batch","batch-normalization","classification","cuda","deep-learning","dnn","iris-dataset"],"created_at":"2025-03-27T22:36:22.849Z","updated_at":"2026-05-02T05:07:46.843Z","avatar_url":"https://github.com/cserajdeep.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Neural Network   \n(1) BN_DNN with 4 layers and 1 output layer. The model gives 100% test accuracy for Iris 7:3 split. \u003cbr\u003e \n(2) DNN_LITE with 2 layers and 1 output layer. The model provides 91.11% test accuracy for same 7:3 split.\n\n\u003ctable style=\"width:50%\"\u003e\n  \u003ctr\u003e\n    \u003cth\u003eModel\u003c/th\u003e\n    \u003cth\u003eAccuracy (%)\u003c/th\u003e\n    \u003cth\u003eAUC\u003c/th\u003e \n    \u003cth\u003e#Param\u003c/\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003eBN_DNN\u003c/td\u003e\n    \u003ctd\u003e100\u003c/td\u003e\n    \u003ctd\u003e1.00\u003c/td\u003e\n    \u003ctd\u003e202,755\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003eDNN_LITE\u003c/td\u003e\n    \u003ctd\u003e91.11\u003c/td\u003e\n    \u003ctd\u003e0.978\u003c/td\u003e\n    \u003ctd\u003e2,953\u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cp\u003e\u003cstrong\u003eUpdated:\u003c/strong\u003e 26-June-2021.\u003c/p\u003e\n\n\n# Heavy Neural Architecture (BN_DNN)\n```ruby\nclass BN_DNN(nn.Module):\n    \"\"\"Feedfoward neural network with 4 hidden layer\"\"\"\n    def __init__(self, in_size, out_size):\n        super().__init__()\n        # hidden layer 1\n        self.linear1 = nn.Linear(in_size, 256)\n        nn.BatchNorm1d(256)    #applying batch norm\n        # hidden layer 2\n        self.linear2 = nn.Linear(256, 512)\n        nn.BatchNorm1d(512)    #applying batch norm\n        # hidden layer 3\n        self.linear3 = nn.Linear(512, 128)\n        nn.BatchNorm1d(128)    #applying batch norm\n        # hidden layer 4\n        self.linear4 = nn.Linear(128, 32)\n        nn.BatchNorm1d(32)    #applying batch norm\n        # output layer\n        self.linear5 = nn.Linear(32, out_size)\n```\n# Light-weight Neural Architecture (DNN_LITE)\n```ruby\nclass DNN_LITE(nn.Module):\n    def __init__(self, input_dim, out_dim):\n        super(DNN_LITE, self).__init__()\n        self.layer1 = nn.Linear(input_dim, 50)\n        nn.BatchNorm1d(50)\n        self.layer2 = nn.Linear(50, 50)\n        nn.BatchNorm1d(50)\n        self.layer3 = nn.Linear(50, out_dim)\n```\n\n# Batch Normalized DNN\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcserajdeep%2Fdnn-iris-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcserajdeep%2Fdnn-iris-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcserajdeep%2Fdnn-iris-pytorch/lists"}