{"id":14958948,"url":"https://github.com/mishig25/vizconvnets","last_synced_at":"2025-07-28T19:32:24.674Z","repository":{"id":59917720,"uuid":"127087537","full_name":"mishig25/vizconvnets","owner":"mishig25","description":"Visualizing 2D Convolutional Layers ","archived":false,"fork":false,"pushed_at":"2018-12-05T00:24:57.000Z","size":56240,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-22T04:41:53.396Z","etag":null,"topics":["deeplearning","tensorflow","tensorflow-experiments","tensorflowjs"],"latest_commit_sha":null,"homepage":"https://mishig25.github.io/vizconvnets/","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/mishig25.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}},"created_at":"2018-03-28T05:18:26.000Z","updated_at":"2024-02-04T00:38:34.000Z","dependencies_parsed_at":"2022-09-25T07:21:05.164Z","dependency_job_id":null,"html_url":"https://github.com/mishig25/vizconvnets","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/mishig25%2Fvizconvnets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mishig25%2Fvizconvnets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mishig25%2Fvizconvnets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mishig25%2Fvizconvnets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mishig25","download_url":"https://codeload.github.com/mishig25/vizconvnets/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":227950629,"owners_count":17846331,"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":["deeplearning","tensorflow","tensorflow-experiments","tensorflowjs"],"created_at":"2024-09-24T13:18:34.460Z","updated_at":"2024-12-03T15:46:03.509Z","avatar_url":"https://github.com/mishig25.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# VizConvnets\n### Visualizing Channels of 2D Convolutional Layers through [Tensorflow.js](https://js.tensorflow.org)\nPersonal Project\n\n#### Check out the Live Demo: [https://mishig25.github.io/vizconvnets/](https://mishig25.github.io/vizconvnets/)\n\n\u003cimg src=\"https://github.com/mishig25/vizconvnets/raw/master/frontend/dist/demo.gif\" width=\"300\"\u003e\n\n#### Description:\n\nAfter [AlexNet](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf) won ImageNet 2012, popularity and usage of convnets have increased exponentially.\nVisualizing channels/filters of conv layers turned out to be a powerful tool for analyzing how Convolutional Neural Networks work. [Zeiler and Fergus](https://arxiv.org/pdf/1311.2901.pdf) were one of the first people to visualize convnets throughly and went on to win ImageNet 2013.\nAfterwards, there was a plethora of papers and demos about visualizing convnets, including [the popular one by Yosinski](http://yosinski.com/deepvis).\n\nThis project is a continuation of the convnet visualizing trend. By using Tensorflow.js and [MobileNet](https://arxiv.org/abs/1704.04861), an efficient CNN architecture, the project visualizes sample channels/filters from MobileNet and does so through web browser only.\n\n### Contents of the repository:\n* [Model](https://github.com/mishig25/vizconvnets/tree/master/model)\nActivation model is created through Keras Functionall API in Jupyter Notebooks.\n* [Frontend](https://github.com/mishig25/vizconvnets/tree/master/frontend)\nUsing Tensorflowjs and HTML5 Canvas to create a convnet visualizations in web-browser environemnt.\n\n### Development:\n```bash\ngit clone https://github.com/mishig25/vizconvnets.git\ncd ./vizconvnets\ncd frontend\nyarn\nyarn watch\n```\n\n#### License\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmishig25%2Fvizconvnets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmishig25%2Fvizconvnets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmishig25%2Fvizconvnets/lists"}