{"id":13784091,"url":"https://github.com/Cyril9227/Keras_AttentiveNormalization","last_synced_at":"2025-05-11T19:32:17.154Z","repository":{"id":215858834,"uuid":"203748092","full_name":"Cyril9227/Keras_AttentiveNormalization","owner":"Cyril9227","description":"Unofficial Keras implementation of the paper Attentive Normalization.","archived":false,"fork":false,"pushed_at":"2020-02-12T05:52:30.000Z","size":245,"stargazers_count":29,"open_issues_count":0,"forks_count":5,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-08-03T19:08:30.004Z","etag":null,"topics":["attention-mechanism","batch-normalization","deep-learning","keras","keras-tensorflow"],"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/Cyril9227.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":"2019-08-22T08:22:24.000Z","updated_at":"2024-01-04T16:37:01.000Z","dependencies_parsed_at":null,"dependency_job_id":"0d75d309-7dd6-4422-84cf-29677f964ba1","html_url":"https://github.com/Cyril9227/Keras_AttentiveNormalization","commit_stats":null,"previous_names":["cyril9227/keras_attentivenormalization"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cyril9227%2FKeras_AttentiveNormalization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cyril9227%2FKeras_AttentiveNormalization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cyril9227%2FKeras_AttentiveNormalization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cyril9227%2FKeras_AttentiveNormalization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Cyril9227","download_url":"https://codeload.github.com/Cyril9227/Keras_AttentiveNormalization/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225086554,"owners_count":17418746,"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","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":["attention-mechanism","batch-normalization","deep-learning","keras","keras-tensorflow"],"created_at":"2024-08-03T19:00:35.292Z","updated_at":"2024-11-17T20:31:27.533Z","avatar_url":"https://github.com/Cyril9227.png","language":"Jupyter Notebook","funding_links":[],"categories":["2019"],"sub_categories":[],"readme":"# Attentive Normalization\nThis repository is an unofficial Keras implementation of the paper [Attentive Normalization](https://arxiv.org/abs/1908.01259) by [Xilai Li](https://github.com/xilaili), [Wei Sun](https://github.com/WillSuen) and [Tianfu Wu](https://github.com/tfwu).\n\nThe official implementation will be released here : https://github.com/ivMCL/\n## Introduction\nAttentive Normalization (AN) is an attention-based version of BN which recalibrates channel information of BN. AN absorbs the [Squeeze-and-Excitation (SE) mechanism](https://arxiv.org/abs/1709.01507) into the affine transformation of BN. AN learns a small number of scale and offset parameters per channel (i.e., different affine transformations). Their weighted sums (i.e., mixture) are used in the final affine transformation. The weights are instance-specific and learned in a way that channel-wise attention is considered, similar in spirit to the squeeze module in the SE unit. This can be used as a drop-in replacement of standard BatchNormalization layer. \n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"img/AN.PNG\"\u003e\n\u003c/p\u003e\n\n## Usage\nPlease refer to the notebook for an usage example.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCyril9227%2FKeras_AttentiveNormalization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCyril9227%2FKeras_AttentiveNormalization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCyril9227%2FKeras_AttentiveNormalization/lists"}