{"id":15627920,"url":"https://github.com/jacobgil/keras-cam","last_synced_at":"2025-04-09T12:09:07.772Z","repository":{"id":139917284,"uuid":"66105249","full_name":"jacobgil/keras-cam","owner":"jacobgil","description":"Keras implementation of class activation mapping","archived":false,"fork":false,"pushed_at":"2017-08-05T02:53:50.000Z","size":459,"stargazers_count":335,"open_issues_count":10,"forks_count":104,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-04-02T11:04:29.366Z","etag":null,"topics":["deep-learning","deep-learning-visualization","keras","visualization"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/jacobgil.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-08-19T18:52:39.000Z","updated_at":"2024-03-16T18:01:50.000Z","dependencies_parsed_at":"2023-04-02T13:02:51.993Z","dependency_job_id":null,"html_url":"https://github.com/jacobgil/keras-cam","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/jacobgil%2Fkeras-cam","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacobgil%2Fkeras-cam/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacobgil%2Fkeras-cam/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacobgil%2Fkeras-cam/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jacobgil","download_url":"https://codeload.github.com/jacobgil/keras-cam/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248036067,"owners_count":21037092,"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":["deep-learning","deep-learning-visualization","keras","visualization"],"created_at":"2024-10-03T10:19:58.375Z","updated_at":"2025-04-09T12:09:07.735Z","avatar_url":"https://github.com/jacobgil.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Keras implementation of class activation mapping\n\nPaper / project page: http://cnnlocalization.csail.mit.edu\n\nPaper authors' code with Caffe / matcaffe interface: https://github.com/metalbubble/CAM\n\n\nBlog post on this repository: http://jacobcv.blogspot.com/2016/08/class-activation-maps-in-keras.html \n\nCheckpoint with person/not person weights: https://drive.google.com/open?id=0B1l5JSkBbENBdk95ZW1DOUhqQUE\n\n![enter image description here](https://raw.githubusercontent.com/jacobgil/keras-cam/master/examples/mona_lisa.jpg)\n\n\nThis project implements class activation maps with Keras.\n\nClass activation maps are a simple technique to get the image regions relevant to a certain class.\n\nThis was fined tuned on VGG16 with images from here: \nhttp://pascal.inrialpes.fr/data/human\n\nThe model in model.py is a two category classifier, used to classify person / not a person.\n\n\tpython cam.py --model_path cam_checkpoint.hdf5 --image_path=image.jpg\n\n    usage: cam.py [-h] [--train TRAIN] [--image_path IMAGE_PATH]\n              [--output_path OUTPUT_PATH] [--model_path MODEL_PATH]\n              [--dataset_path DATASET_PATH]\n\n\toptional arguments:\n\t  -h, --help            show this help message and exit\n\t  --train TRAIN         Train the network or visualize a CAM\n\t  --image_path IMAGE_PATH\n\t                        Path of an image to run the network on\n\t  --output_path OUTPUT_PATH\n\t                        Path of an image to run the network on\n\t  --model_path MODEL_PATH\n\t                        Path of the trained model\n\t  --dataset_path DATASET_PATH\n\t                        Path to image dataset. Should have pos/neg folders,\n\t                        like in the inria person dataset.\n\t                        http://pascal.inrialpes.fr/data/human/\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacobgil%2Fkeras-cam","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjacobgil%2Fkeras-cam","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacobgil%2Fkeras-cam/lists"}