{"id":13591920,"url":"https://github.com/keplr-io/quiver","last_synced_at":"2026-02-19T16:33:45.177Z","repository":{"id":13127487,"uuid":"73647442","full_name":"keplr-io/quiver","owner":"keplr-io","description":"Interactive convnet features visualization for Keras","archived":false,"fork":false,"pushed_at":"2020-09-04T00:19:41.000Z","size":529,"stargazers_count":1790,"open_issues_count":32,"forks_count":225,"subscribers_count":55,"default_branch":"master","last_synced_at":"2025-10-20T16:08:27.845Z","etag":null,"topics":["convolutional-neural-networks","deep-learning","visualization"],"latest_commit_sha":null,"homepage":"https://keplr-io.github.io/quiver/","language":"JavaScript","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/keplr-io.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":"2016-11-13T22:35:44.000Z","updated_at":"2025-10-19T20:36:29.000Z","dependencies_parsed_at":"2022-08-07T07:01:02.881Z","dependency_job_id":null,"html_url":"https://github.com/keplr-io/quiver","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/keplr-io/quiver","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keplr-io%2Fquiver","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keplr-io%2Fquiver/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keplr-io%2Fquiver/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keplr-io%2Fquiver/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/keplr-io","download_url":"https://codeload.github.com/keplr-io/quiver/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keplr-io%2Fquiver/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29622017,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-19T13:04:20.082Z","status":"ssl_error","status_checked_at":"2026-02-19T13:03:33.775Z","response_time":117,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["convolutional-neural-networks","deep-learning","visualization"],"created_at":"2024-08-01T16:01:03.692Z","updated_at":"2026-02-19T16:33:45.143Z","avatar_url":"https://github.com/keplr-io.png","language":"JavaScript","funding_links":[],"categories":["JavaScript","Visualization","Keras Cheatsheet"],"sub_categories":["Model Visualization"],"readme":"# Quiver\n[![Gitter chat](https://badges.gitter.im/gitterHQ/gitter.png)](https://gitter.im/quiverEngine/Lobby)\n\nInteractive convnet features visualization for Keras\n\n\n![gzqll3](https://cloud.githubusercontent.com/assets/5866348/20253975/f3d56f14-a9e4-11e6-9693-9873a18df5d3.gif)\n\n\n\n\n**The quiver workflow**\n\n[Video Demo](https://www.youtube.com/watch?edit=vd\u0026v=tgRW3BRi_FA)\n\n1. Build your model in keras\n\n    ```python\n    model = Model(...)\n    ```\n2. Launch the visualization dashboard with 1 line of code\n\n    ```python\n    quiver_engine.server.launch(model, classes=['cat','dog'], input_folder='./imgs')\n    ```\n3. Explore layer activations on all the different images in your input folder.\n\n\n## Quickstart\n\n**Installation**\n\n```bash\n    pip install quiver_engine\n```\n\nIf you want the latest version from the repo\n\n```bash\n    pip install git+git://github.com/keplr-io/quiver.git\n```\n\n\n**Usage**\n\nTake your keras `model`, launching Quiver is a one-liner.\n\n```python\n    from quiver_engine import server\n    server.launch(model)\n```\n\nThis will launch the visualization at `localhost:5000`\n\n**Options**\n\n```python\n    server.launch(\n        model, # a Keras Model\n\n        classes, # list of output classes from the model to present (if not specified 1000 ImageNet classes will be used)\n\n        top, # number of top predictions to show in the gui (default 5)\n\n        # where to store temporary files generatedby quiver (e.g. image files of layers)\n        temp_folder='./tmp',\n\n        # a folder where input images are stored\n        input_folder='./',\n\n        # the localhost port the dashboard is to be served on\n        port=5000,\n        # custom data mean\n        mean=[123.568, 124.89, 111.56],\n        # custom data standard deviation\n        std=[52.85, 48.65, 51.56]\n    )\n```\n\n## Development\n\n**Building from master**\n\nCheck out this repository and run\n\n```bash\ncd quiver_engine\npython setup.py develop\n```\n\n**Building the Client**\n\n```bash\n    cd quiverboard\n    npm install\n    export QUIVER_URL=localhost:5000 # or whatever you set your port to be\n    npm start\n```\n\nNote this will run your web application with webpack and hot reloading. If you don't care about that, or are only in this section because pip install somehow failed for you, you should tell it to simply build the javascript files instead\n\n```\n    npm run deploy:prod\n```\n\n\n## Credits\n\n- This is essentially an implementation of some ideas of [deepvis](https://github.com/yosinski/deep-visualization-toolbox) and related works.\n- A lot of the pre/pos/de processing code was taken from [here](https://github.com/fchollet/deep-learning-models) and other writings of [fchollet](https://github.com/fchollet).\n- The dashboard makes use of [react-redux-starter-kit](https://github.com/davezuko/react-redux-starter-kit)\n\n## Citing Quiver\n\n```\nmisc{bianquiver,\n  title={Quiver},\n  author={Bian, Jake},\n  year={2016},\n  publisher={GitHub},\n  howpublished={\\url{https://github.com/keplr-io/quiver}},\n}\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeplr-io%2Fquiver","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkeplr-io%2Fquiver","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeplr-io%2Fquiver/lists"}