{"id":18861126,"url":"https://github.com/vivelev/senet-flow","last_synced_at":"2026-05-07T05:32:34.959Z","repository":{"id":83970326,"uuid":"169324313","full_name":"VIVelev/SENet-flow","owner":"VIVelev","description":"Squeeze-and-Excitation Network - implementation in TensorFlow","archived":false,"fork":false,"pushed_at":"2019-02-10T10:42:41.000Z","size":648,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-02-15T07:14:37.558Z","etag":null,"topics":["neural-network","squeeze-and-excitation","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/VIVelev.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":"2019-02-05T22:39:19.000Z","updated_at":"2020-12-11T17:39:30.000Z","dependencies_parsed_at":null,"dependency_job_id":"e84ec796-d4fe-4fa8-8874-db55fece2ea1","html_url":"https://github.com/VIVelev/SENet-flow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VIVelev%2FSENet-flow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VIVelev%2FSENet-flow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VIVelev%2FSENet-flow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VIVelev%2FSENet-flow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/VIVelev","download_url":"https://codeload.github.com/VIVelev/SENet-flow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239800405,"owners_count":19699129,"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":["neural-network","squeeze-and-excitation","tensorflow"],"created_at":"2024-11-08T04:28:11.091Z","updated_at":"2026-02-09T08:30:16.455Z","avatar_url":"https://github.com/VIVelev.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SENet-flow\nSqueeze-and-Excitation Network (SENet) implementation in [TensorFlow](https://www.tensorflow.org)\n\n***You can find the original paper [here](https://arxiv.org/pdf/1709.01507.pdf)*** \u003cbr\u003e\nwritten by Jie Hu, Li Shen, Gang Sun\n\nIf you want to see ***the original author's code***, please refer to this [link](https://github.com/hujie-frank/SENet)\n\n## Requirements\n - Python 3.x\n - Tensorflow 1.x\n\n## Idea\n### What is SENet?\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/VIVelev/SENet-flow/blob/master/figures/SE-pipeline.jpg\"\u003e\n\u003c/div\u003e\n\u003cp align=\"center\"\u003e\n  Figure 1: Diagram of a Squeeze-and-Excitation building block\n\u003c/p\u003e\n\n### How do you integrate it in existing powerful architectures? (Inception Network, ResNet)\n\u003cdiv align=\"center\"\u003e\n   \u003cimg src=\"https://github.com/VIVelev/SENet-flow/blob/master/figures/SE-Inception-module.jpg\" width=\"420\"\u003e\n  \u003cimg src=\"https://github.com/VIVelev/SENet-flow/blob/master/figures/SE-ResNet-module.jpg\"  width=\"420\"\u003e\n\u003c/div\u003e\n\u003cp align=\"center\"\u003e\n  Figure 2: Schema of SE-Inception and SE-ResNet modules\n\u003c/p\u003e\n\n### Hyper-parameters\n - Reduction Ratio - controls the bottleneck size (the number of units in the bottleneck dense layer)\n\u003cdiv align=\"center\"\u003e\n   \u003cimg src=\"https://github.com/VIVelev/SENet-flow/blob/master/figures/Reduction-Ratio.jpg\" width=\"420\"\u003e\n\u003c/div\u003e\n\u003cp align=\"center\"\u003e\n  Figure 3: Different choices for the Reduction Ratio hyperparameter and the consequent results\n\u003c/p\u003e\n\n## Why should you use Squeeze-and-Excitation Netwroks\n### State-of-the-art performace on ILSVRC 2017 (ImageNet 2017 dataset)\n\u003cdiv align=\"center\"\u003e\n   \u003cimg src=\"https://github.com/VIVelev/SENet-flow/blob/master/figures/State-of-the-art.jpg\" width=\"420\"\u003e\n\u003c/div\u003e\n\u003cp align=\"center\"\u003e\n  Figure 4: State-of-the-art performace on ILSVRC 2017\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvivelev%2Fsenet-flow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvivelev%2Fsenet-flow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvivelev%2Fsenet-flow/lists"}