{"id":19178586,"url":"https://github.com/cloud-cv/grad-cam","last_synced_at":"2026-06-20T22:30:18.137Z","repository":{"id":50296194,"uuid":"63409178","full_name":"Cloud-CV/Grad-CAM","owner":"Cloud-CV","description":":rainbow: :camera: Gradient-weighted Class Activation Mapping (Grad-CAM) Demo","archived":false,"fork":false,"pushed_at":"2018-08-13T18:49:48.000Z","size":6000,"stargazers_count":110,"open_issues_count":8,"forks_count":26,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-01-04T02:52:22.089Z","etag":null,"topics":["cnn","deep-learning","demo","grad-cam","machine-learning","torch"],"latest_commit_sha":null,"homepage":"http://gradcam.cloudcv.org/","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Cloud-CV.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-07-15T09:20:25.000Z","updated_at":"2024-12-27T03:14:24.000Z","dependencies_parsed_at":"2022-08-25T11:51:17.381Z","dependency_job_id":null,"html_url":"https://github.com/Cloud-CV/Grad-CAM","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cloud-CV%2FGrad-CAM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cloud-CV%2FGrad-CAM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cloud-CV%2FGrad-CAM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Cloud-CV%2FGrad-CAM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Cloud-CV","download_url":"https://codeload.github.com/Cloud-CV/Grad-CAM/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240255321,"owners_count":19772597,"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":["cnn","deep-learning","demo","grad-cam","machine-learning","torch"],"created_at":"2024-11-09T10:40:02.171Z","updated_at":"2026-06-20T22:30:18.107Z","avatar_url":"https://github.com/Cloud-CV.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# Grad-CAM: Gradient-weighted Class Activation Mapping\n\n[![Join the chat at https://gitter.im/Cloud-CV/Grad-CAM](https://badges.gitter.im/Cloud-CV/Grad-CAM.svg)](https://gitter.im/Cloud-CV/Grad-CAM?utm_source=badge\u0026utm_medium=badge\u0026utm_campaign=pr-badge\u0026utm_content=badge)\n\nGrad-CAM uses the class-specific gradient information flowing into the final convolutional layer of a CNN to produce a coarse localization map of the important regions in the image. It is a novel technique for making CNN more 'transparent' by producing **visual explanations** i.e visualizations showing what evidence in the image supports a prediction. You can play with Grad-CAM demonstrations at the following links:\n\n**Arxiv Paper Link**: https://arxiv.org/abs/1610.02391\n\n### Grad-CAM VQA Demo: http://gradcam.cloudcv.org/vqa\n\n\n![Imgur](http://i.imgur.com/6jB4lAq.gif)\n\n### Grad-CAM Classification Demo: http://gradcam.cloudcv.org/classification\n\n\n![Imgur](http://i.imgur.com/a1IiQg4.gif)\n\n### Grad-CAM Captioning Demo: http://gradcam.cloudcv.org/captioning\n\n\n![Imgur](http://i.imgur.com/BsOOpIn.gif)\n\n## Installing / Getting started\n\nWe use RabbitMQ to queue the submitted jobs. Also, we use Redis as backend for realtime communication using websockets.\n\nAll the instructions for setting Grad-CAM from scratch can be found  [here](https://github.com/Cloud-CV/Grad-CAM/blob/master/INSTALLATION.md)\n\nNote: For best results, its recommended to run the Grad-CAM demo on GPU enabled machines.\n\n## Interested in Contributing?\n\nCloud-CV always welcomes new contributors to learn the new cutting edge technologies. If you'd like to contribute, please fork the repository and use a feature branch. Pull requests are warmly welcome.\n\nif you have more questions about the project, then you can talk to us on our [Gitter Channel](https://gitter.im/Cloud-CV/Grad-CAM).  \n\n## Acknowledgements\n\n- [VQA_LSTM_CNN](https://github.com/VT-vision-lab/VQA_LSTM_CNN)\n- [HieCoAttenVQA](https://github.com/jiasenlu/HieCoAttenVQA)\n- [NeuralTalk2](https://github.com/karpathy/neuraltalk2/)\n- [PyTorch](https://github.com/hughperkins/pytorch)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcloud-cv%2Fgrad-cam","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcloud-cv%2Fgrad-cam","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcloud-cv%2Fgrad-cam/lists"}