{"id":20767826,"url":"https://github.com/kyzn/minibatchimagemorphing","last_synced_at":"2026-04-29T23:32:46.141Z","repository":{"id":73424457,"uuid":"60922315","full_name":"kyzn/MiniBatchImageMorphing","owner":"kyzn","description":"An attempt at introducing morphed in between images to mini batches while training a Deep Neural Network.","archived":false,"fork":false,"pushed_at":"2020-06-13T19:05:57.000Z","size":176,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-12-26T11:43:45.217Z","etag":null,"topics":["deep-learning","machine-learning","mnist","neural-network","ucsc"],"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/kyzn.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":"2016-06-11T18:38:07.000Z","updated_at":"2020-02-18T04:02:44.000Z","dependencies_parsed_at":null,"dependency_job_id":"7092cf09-65a1-4c07-a3bb-0cdb2b0d1de2","html_url":"https://github.com/kyzn/MiniBatchImageMorphing","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/kyzn/MiniBatchImageMorphing","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyzn%2FMiniBatchImageMorphing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyzn%2FMiniBatchImageMorphing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyzn%2FMiniBatchImageMorphing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyzn%2FMiniBatchImageMorphing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kyzn","download_url":"https://codeload.github.com/kyzn/MiniBatchImageMorphing/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyzn%2FMiniBatchImageMorphing/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32448399,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-29T22:27:22.272Z","status":"ssl_error","status_checked_at":"2026-04-29T22:10:49.234Z","response_time":110,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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-learning","machine-learning","mnist","neural-network","ucsc"],"created_at":"2024-11-17T11:33:34.254Z","updated_at":"2026-04-29T23:32:46.125Z","avatar_url":"https://github.com/kyzn.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Image Morphing for Mini Batches in DNN\n\n![An example for morphing: each row is a different digit.](https://github.com/kyzn/MiniBatchImageMorphing/raw/master/0%20Example/Example.png)\n\nAs part of UCSC - CS218 \"Deep Learning\" class, we wanted to work on possible ways to improve our test accuracy. One idea was to introduce more images to mini-batches. We did it by creating new images. \n\nThis code is based on [Michael Nielsen's code](https://github.com/mnielsen/neural-networks-and-deep-learning/blob/master/README.md), which uses MNIST dataset. We also used the same data.\n\nTo get the data file, please right click and save [mnist.pkl.gz](https://github.com/mnielsen/neural-networks-and-deep-learning/raw/master/data/mnist.pkl.gz).\n\n\n## Results\n\n|                     | Min Test Cost | Max Test Accuracy |\n| ------------------- | ------------- | ----------------- |\n| Benchmark           | **0.6108**    | **97.00%**        |\n| With Image Morphing |   1.3728      |   95.07%          |\n\n\n## License\n\nPlease visit https://github.com/mnielsen/neural-networks-and-deep-learning/blob/master/README.md for license details of *Code samples for \"Neural Networks and Deep Learning\"*.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkyzn%2Fminibatchimagemorphing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkyzn%2Fminibatchimagemorphing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkyzn%2Fminibatchimagemorphing/lists"}