{"id":27935896,"url":"https://github.com/deepankaracharyya/intermediate_representation","last_synced_at":"2026-04-15T20:01:30.105Z","repository":{"id":128778546,"uuid":"249679699","full_name":"DeepankarAcharyya/Intermediate_Representation","owner":"DeepankarAcharyya","description":"In this project, I will try to present a visual representation of the what the convnets learn during training. ","archived":false,"fork":false,"pushed_at":"2020-03-24T19:50:32.000Z","size":5849,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-07T06:51:38.599Z","etag":null,"topics":["deep-neural-networks","keras","keras-models","representation-learning"],"latest_commit_sha":null,"homepage":null,"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/DeepankarAcharyya.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2020-03-24T10:36:10.000Z","updated_at":"2020-05-11T09:09:54.000Z","dependencies_parsed_at":"2023-03-25T15:51:55.259Z","dependency_job_id":null,"html_url":"https://github.com/DeepankarAcharyya/Intermediate_Representation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/DeepankarAcharyya/Intermediate_Representation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepankarAcharyya%2FIntermediate_Representation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepankarAcharyya%2FIntermediate_Representation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepankarAcharyya%2FIntermediate_Representation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepankarAcharyya%2FIntermediate_Representation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DeepankarAcharyya","download_url":"https://codeload.github.com/DeepankarAcharyya/Intermediate_Representation/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DeepankarAcharyya%2FIntermediate_Representation/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266420082,"owners_count":23925880,"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","status":"online","status_checked_at":"2025-07-22T02:00:09.085Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"robots_txt_url":"https://github.com/robots.txt","online":true,"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":["deep-neural-networks","keras","keras-models","representation-learning"],"created_at":"2025-05-07T06:51:08.213Z","updated_at":"2026-04-15T20:01:25.066Z","avatar_url":"https://github.com/DeepankarAcharyya.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Intermediate_Representation\nIn this project, I will try to present a visual representation of the what the convnets learn during training. \n\nThe representations learned by convnets are highly amenable to visualization, in large because they are representations of visual concepts.\n\n# Findings:\n\u003e * First Layer acts as a collection of various edge detectors.\n\u003e \u003e At this stage, almost all the information present in the initial image is present.\n\u003e * As we go deeper, the activations becomes more abstract and less visually interpretable.\n\u003e \u003e Higher presentations carry increasingly less information about the visual contents of the image and increasingly more information related to the class of the image.\n\u003e * In the following layers, more and more filters are blank, which means that the pattern encoded by the filter isn't found in the input image.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepankaracharyya%2Fintermediate_representation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeepankaracharyya%2Fintermediate_representation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepankaracharyya%2Fintermediate_representation/lists"}