{"id":15958522,"url":"https://github.com/vermavinay982/feature-map-visualizer-grad-ascent","last_synced_at":"2026-04-10T01:04:29.546Z","repository":{"id":185366341,"uuid":"332842353","full_name":"vermavinay982/feature-map-visualizer-grad-ascent","owner":"vermavinay982","description":"What a neural network captures? The filter and feature-maps can be visualized with any image to test with.","archived":false,"fork":false,"pushed_at":"2021-06-14T05:53:45.000Z","size":40021,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-09T20:47:08.056Z","etag":null,"topics":["cnn","deep","deep-learning","dl","feature","filter","keras","maps","neural-network","opencv","python","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vermavinay982.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}},"created_at":"2021-01-25T18:23:11.000Z","updated_at":"2022-09-18T19:08:24.000Z","dependencies_parsed_at":null,"dependency_job_id":"b53e997f-8361-4cf1-8eb2-fc348e404157","html_url":"https://github.com/vermavinay982/feature-map-visualizer-grad-ascent","commit_stats":null,"previous_names":["vermavinay982/feature-map-visualizer-grad-ascent"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vermavinay982%2Ffeature-map-visualizer-grad-ascent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vermavinay982%2Ffeature-map-visualizer-grad-ascent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vermavinay982%2Ffeature-map-visualizer-grad-ascent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vermavinay982%2Ffeature-map-visualizer-grad-ascent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vermavinay982","download_url":"https://codeload.github.com/vermavinay982/feature-map-visualizer-grad-ascent/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247166144,"owners_count":20894652,"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","deep-learning","dl","feature","filter","keras","maps","neural-network","opencv","python","tensorflow"],"created_at":"2024-10-07T14:05:00.674Z","updated_at":"2025-12-30T23:08:25.888Z","avatar_url":"https://github.com/vermavinay982.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Weights-Visualizer-for-CNN\r\nWhat a Neural Network Captures? The filter and feature-maps can be visualized with any image to test with.\r\n\r\nFeauture maps closer to the input of model captures a lot of fine detail in the image as we progress deeper in the model, feature map show less detail.\r\n\r\n\r\n## Heatmaps - What makes Cat different from Monkey\r\n\u003cdiv\u003e\r\n\u003cimg style='display:inline-block;' height=300px width=400px src='outputs/cat_cam.jpg'\u003e\r\n\u003cimg style='display:inline-block;' height=300px width=400px src='outputs/elephant_cam.jpg'\u003e \r\n\u003cimg style='display:inline-block;' height=300px width=400px src='outputs/pug_cam.jpg'\u003e \r\n\u003cimg style='display:inline-block;' height=300px width=400px src='outputs/sq_monkey_cam.jpg'\u003e \r\n\u003c/div\u003e\r\n \r\n\r\n## Convnets Filters - What Activates the ConvNet Most\r\n\u003cdiv\u003e\r\n\u003cimg style='display:inline-block;' height=200px width=200px src='outputs/block4_conv1.jpg'\u003e\r\n\u003cimg style='display:inline-block;' height=200px width=200px src='outputs/block3_conv1.jpg'\u003e\r\n\u003cimg style='display:inline-block;' height=200px width=200px src='outputs/block2_conv1.jpg'\u003e\r\n\u003cimg style='display:inline-block;' height=200px width=200px src='outputs/block1_conv1.jpg'\u003e\r\n\u003c/div\u003e\r\n\r\n\r\n## Feature Map on Bird Image - How Input Changes \r\n  \u003cimg style='display:inline-block;' height=400px width=800px src='outputs/bird/loop_bird.gif'\u003e\r\n\r\nThis pattern was expected as the model abstracts the features from the image into more general concepts that can be used to make a classification still it is not clear from final image the model saw a bird, we generally lose the ability to interpret these deeper feature maps\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvermavinay982%2Ffeature-map-visualizer-grad-ascent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvermavinay982%2Ffeature-map-visualizer-grad-ascent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvermavinay982%2Ffeature-map-visualizer-grad-ascent/lists"}