{"id":21151902,"url":"https://github.com/uranusx86/addernet-on-tensorflow","last_synced_at":"2026-05-06T00:37:49.192Z","repository":{"id":74942616,"uuid":"594420138","full_name":"uranusx86/AdderNet-on-tensorflow","owner":"uranusx86","description":"a implementation of neural network with almost no multiplication with tensorflow 2 (Adder Net)","archived":false,"fork":false,"pushed_at":"2023-02-19T10:58:29.000Z","size":9,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-08-12T16:51:57.602Z","etag":null,"topics":["adder","addernet","ai","artificial-intelligence","cnn","custom-layer","deep-learning","deep-neural-networks","image-classification","implementation","implementation-of-research-paper","keras","lightweight","mnist","neural-network","tensorflow","tensorflow2"],"latest_commit_sha":null,"homepage":"","language":"Python","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/uranusx86.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":"2023-01-28T13:58:36.000Z","updated_at":"2023-02-16T13:15:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"4e0466e9-2d4a-41c5-985c-133762475a76","html_url":"https://github.com/uranusx86/AdderNet-on-tensorflow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/uranusx86/AdderNet-on-tensorflow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uranusx86%2FAdderNet-on-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uranusx86%2FAdderNet-on-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uranusx86%2FAdderNet-on-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uranusx86%2FAdderNet-on-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/uranusx86","download_url":"https://codeload.github.com/uranusx86/AdderNet-on-tensorflow/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uranusx86%2FAdderNet-on-tensorflow/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279013635,"owners_count":26085298,"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":"2025-10-12T02:00:06.719Z","response_time":53,"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":["adder","addernet","ai","artificial-intelligence","cnn","custom-layer","deep-learning","deep-neural-networks","image-classification","implementation","implementation-of-research-paper","keras","lightweight","mnist","neural-network","tensorflow","tensorflow2"],"created_at":"2024-11-20T10:19:50.475Z","updated_at":"2025-10-13T00:41:30.929Z","avatar_url":"https://github.com/uranusx86.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AdderNet-on-tensorflow\na implementation of L1 Convolution and Dense layer with tensorflow 2 (Adder Net).\n\nthis project is still under development.\n\n# Requirement\n* tensorflow 2\n* numpy\n\n# Work log\n\nAt first, the training accuracy was 96% and the testing accuracy was 95.6% on the MNIST dataset.\n\n[2023-02-03] add full-precision gradient, the training accuracy is 97.4% and the testing accuracy is 96.9% on the MNIST dataset.\n\n[2023-02-04] add gradient clipping, the training accuracy is 97.1% and the testing accuracy is 96.4% on the MNIST dataset.\n\n[2023-02-16] add cosine lr, the training accuracy is 99.97% and the testing accuracy is 98.87% on the MNIST dataset.\n\n[2023-02-18] add adaptive gradient scaling, change the optimizer from adam to NAG and increase the epoches to 50, the training accuracy is 99.99% and the testing accuracy is 98.94% on the MNIST dataset.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Furanusx86%2Faddernet-on-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Furanusx86%2Faddernet-on-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Furanusx86%2Faddernet-on-tensorflow/lists"}