{"id":40928274,"url":"https://github.com/tnfru/computer_vision","last_synced_at":"2026-01-22T04:02:05.331Z","repository":{"id":276609893,"uuid":"234569566","full_name":"tnfru/computer_vision","owner":"tnfru","description":"Classification with Deep Learning","archived":false,"fork":false,"pushed_at":"2020-10-07T12:31:18.000Z","size":975,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-09T12:24:02.158Z","etag":null,"topics":["cifar10","computer-vision","mnist","pytorch"],"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/tnfru.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":"2020-01-17T14:51:27.000Z","updated_at":"2020-11-21T20:53:23.000Z","dependencies_parsed_at":"2025-02-09T12:34:11.716Z","dependency_job_id":null,"html_url":"https://github.com/tnfru/computer_vision","commit_stats":null,"previous_names":["tnfru/computer_vision"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/tnfru/computer_vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tnfru%2Fcomputer_vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tnfru%2Fcomputer_vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tnfru%2Fcomputer_vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tnfru%2Fcomputer_vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tnfru","download_url":"https://codeload.github.com/tnfru/computer_vision/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tnfru%2Fcomputer_vision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28653626,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-22T01:17:37.254Z","status":"online","status_checked_at":"2026-01-22T02:00:07.137Z","response_time":144,"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":["cifar10","computer-vision","mnist","pytorch"],"created_at":"2026-01-22T04:02:04.607Z","updated_at":"2026-01-22T04:02:05.321Z","avatar_url":"https://github.com/tnfru.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Computer Vision\n\nIn this repo I will upload all problem statements I tackled using computer vison. \nI am exectuing these Notebooks on Google Colab, which is a fantastic platform\noffering free GPUs and TPUs.\nIn these I am not using transfer learning as it would basically kill the idea\nof learning to design CNN architectures.\n\n## CIFAR-10\n\nWe use a Wide-ResNet and achieve 93.23% accuracy, beating the original ResNet56v1 \nby .2%.\nThis is due to Dropout and the parallell convolutions in conv and identity modules.\n\n## MNIST\n\nMy take on the classic MNIST dataset to classify handwritten digits, which \nachieves 99.6% accuracy.\n\nThere are a PyTorch and a Keras implementations in this repository.\nThe Keras version hit 0.99614 on kaggle. It uses a slightly changed version of\nLeNet5 replacing 5x5 Filter with two 3x3 for non linerarity.\n\nThe PyTorch implementation, which uses a large number of epochs, \nchecks for overfitting and will abort on its own. This version\nwas programmed only on a CPU, hence the small network.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftnfru%2Fcomputer_vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftnfru%2Fcomputer_vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftnfru%2Fcomputer_vision/lists"}