{"id":17312973,"url":"https://github.com/digantamisra98/evonorm","last_synced_at":"2025-08-25T20:10:01.704Z","repository":{"id":131277787,"uuid":"254041477","full_name":"digantamisra98/EvoNorm","owner":"digantamisra98","description":"Unofficial PyTorch Implementation of EvoNorm","archived":false,"fork":false,"pushed_at":"2021-08-29T16:48:01.000Z","size":390,"stargazers_count":121,"open_issues_count":1,"forks_count":17,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-14T13:59:05.136Z","etag":null,"topics":["computer-vision","deep-learning","nas","neural-architecture-search","neural-networks","normalization"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2004.02967","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/digantamisra98.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}},"created_at":"2020-04-08T09:21:35.000Z","updated_at":"2024-06-07T22:10:41.000Z","dependencies_parsed_at":null,"dependency_job_id":"9a3fa29d-db71-4ca2-9086-f09d9bc2bfe1","html_url":"https://github.com/digantamisra98/EvoNorm","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/digantamisra98/EvoNorm","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/digantamisra98%2FEvoNorm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/digantamisra98%2FEvoNorm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/digantamisra98%2FEvoNorm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/digantamisra98%2FEvoNorm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/digantamisra98","download_url":"https://codeload.github.com/digantamisra98/EvoNorm/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/digantamisra98%2FEvoNorm/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272124753,"owners_count":24877720,"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":"2025-08-25T02:00:12.092Z","response_time":1107,"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":["computer-vision","deep-learning","nas","neural-architecture-search","neural-networks","normalization"],"created_at":"2024-10-15T12:45:15.832Z","updated_at":"2025-08-25T20:10:01.660Z","avatar_url":"https://github.com/digantamisra98.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Evolving Normalization-Activation Layers\n\n*Google AI and DeepMind*\n\n- [x] Implement EvoNorm S0 and B0 with Training Mode support\n- [x] Solve Shape Error with group_std and instance_std functions\n- [x] Solve NaN Error Issue with S0\n- [x] Fix Error with shape in running variance calculation in EvoNorm B0\n- [x] Solve NaN Error Issue with B0\n\n\u003cdiv style=\"text-align:center\"\u003e\u003cimg src =\"figures/evonorm.PNG\"  width=\"1000\"/\u003e\u003c/div\u003e\n\u003cp\u003e\n\u003cem\u003eFigure 1. Left: Computation graph of a searched normalization activation layer that is batch-independent, named EvoNorm-S0.      Right: ResNet-50 results with EvoNorm-S0 as the batch size over 8 workers varies from 1024 to 32 on ImageNet. EvoNorm-S0 also outperforms both BN and GN-based layers on MobileNetV2 and Mask R-CNN.\n\u003c/em\u003e\n\u003c/p\u003e\n\n## Usage: \n\n```\nfrom evonorm2d import EvoNorm2D\n# For B0 version\nevoB0 = EvoNorm2D(input, affine = True, version = 'B0', training = True)\n\n# For S0 version \nevoS0 = EvoNorm2D(input)\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdigantamisra98%2Fevonorm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdigantamisra98%2Fevonorm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdigantamisra98%2Fevonorm/lists"}