{"id":20402587,"url":"https://github.com/vbhavank/challenge_question2_catdog_vasu","last_synced_at":"2026-05-09T08:07:12.888Z","repository":{"id":106726710,"uuid":"117636537","full_name":"vbhavank/Challenge_question2_catdog_vasu","owner":"vbhavank","description":"This is a project for a CatvsDog classifier using a very limited number of samples","archived":false,"fork":false,"pushed_at":"2018-01-30T09:56:45.000Z","size":271,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-05T01:45:14.058Z","etag":null,"topics":["catvsdog-classifier","computer-vision","deep-learning","machine-learning","python","tensorflow"],"latest_commit_sha":null,"homepage":"","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/vbhavank.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":"2018-01-16T05:40:36.000Z","updated_at":"2018-01-30T09:58:21.000Z","dependencies_parsed_at":null,"dependency_job_id":"f1bc921a-84d8-4724-b1c9-6833644e9719","html_url":"https://github.com/vbhavank/Challenge_question2_catdog_vasu","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vbhavank/Challenge_question2_catdog_vasu","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vbhavank%2FChallenge_question2_catdog_vasu","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vbhavank%2FChallenge_question2_catdog_vasu/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vbhavank%2FChallenge_question2_catdog_vasu/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vbhavank%2FChallenge_question2_catdog_vasu/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vbhavank","download_url":"https://codeload.github.com/vbhavank/Challenge_question2_catdog_vasu/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vbhavank%2FChallenge_question2_catdog_vasu/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32811662,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-08T08:22:46.396Z","status":"online","status_checked_at":"2026-05-09T02:00:06.633Z","response_time":123,"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":["catvsdog-classifier","computer-vision","deep-learning","machine-learning","python","tensorflow"],"created_at":"2024-11-15T04:54:45.494Z","updated_at":"2026-05-09T08:07:12.848Z","avatar_url":"https://github.com/vbhavank.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Training a CNN with just 20 images\n\n\nAuthor: \nBhavan Vasu\nGraduate Research Assistant, \nReal-time and computer vision lab,\nRochester Institute of Technology,\nNew York-14623\nbxv7657@rit.edu\n\nRequirements :\n1) Numpy\n2) matplotlib\n3) tflearn\n4) Opencv2\n\nAdd the training and testing samples into two folders in the current directory,named 'train' and 'test' respectively.\n\nAlexnet was chosen for the implementation of a CatvsDog classifier using Tensorflow and python.(Check network graph for layer information)\nThe network is trained on 18 images and validated on 2 images during training.\n\nThe network is trained for just 12 epochs with a batch size of 16 with a learning rate of 1e-5.\n\nThe network manages to achieve a test accuracy of about 50-70%, measured from visual inspection of the 20 unknown test images. \n \n\nRun the 'catd.py' file for the CatvsDog classifier.\n\nTo test and train:\n\n$ python catd.py\n\nTo run tensorboard for network visualization\n\n$tensorboard --logdir=\"logs\"\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvbhavank%2Fchallenge_question2_catdog_vasu","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvbhavank%2Fchallenge_question2_catdog_vasu","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvbhavank%2Fchallenge_question2_catdog_vasu/lists"}