{"id":20009934,"url":"https://github.com/i008/deepcounting","last_synced_at":"2026-06-09T16:31:22.773Z","repository":{"id":138782144,"uuid":"82089718","full_name":"i008/deepcounting","owner":"i008","description":"neural networks are cool but can they count?","archived":false,"fork":false,"pushed_at":"2017-03-09T21:12:29.000Z","size":4179,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-08-14T19:28:36.956Z","etag":null,"topics":["convolutional-neural-networks","data-augumentation","data-generation"],"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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/i008.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":"2017-02-15T17:57:51.000Z","updated_at":"2017-02-26T11:06:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"be85578e-1819-4c95-8fb8-4420444e87b5","html_url":"https://github.com/i008/deepcounting","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/i008/deepcounting","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/i008%2Fdeepcounting","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/i008%2Fdeepcounting/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/i008%2Fdeepcounting/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/i008%2Fdeepcounting/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/i008","download_url":"https://codeload.github.com/i008/deepcounting/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/i008%2Fdeepcounting/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34116456,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-09T02:00:06.510Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","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":["convolutional-neural-networks","data-augumentation","data-generation"],"created_at":"2024-11-13T07:17:32.724Z","updated_at":"2026-06-09T16:31:22.538Z","avatar_url":"https://github.com/i008.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"### Idea\n\nThe question is simple, what happens if we generate images with some kind of objects on them (circles for example) and train \na CNN giving it only the count of the objects as the target variable. Will it learn to count? will it learn to segment properly?  \nThe biggest challange of the image-generation part is to avoid data-leakage  for example the network fitting to the total-area of the foreground instead of the object count.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fi008%2Fdeepcounting","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fi008%2Fdeepcounting","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fi008%2Fdeepcounting/lists"}