{"id":17695595,"url":"https://github.com/kushrm2803/mnist_gan","last_synced_at":"2026-05-03T23:34:12.005Z","repository":{"id":258355405,"uuid":"873734986","full_name":"kushrm2803/mnist_gan","owner":"kushrm2803","description":"Generative Adversarial Network (GAN) to generate handwritten digits similar to those in the MNIST dataset","archived":false,"fork":false,"pushed_at":"2024-10-16T17:46:53.000Z","size":4910,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-08-11T05:34:37.602Z","etag":null,"topics":["ann","cnn","deep-learning","keras","mnist","tensorflow"],"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/kushrm2803.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":"2024-10-16T16:20:03.000Z","updated_at":"2024-10-16T17:46:57.000Z","dependencies_parsed_at":"2024-10-18T16:04:53.818Z","dependency_job_id":"854b873e-e098-4f6f-b0c0-4a61509909d8","html_url":"https://github.com/kushrm2803/mnist_gan","commit_stats":null,"previous_names":["kushrm2803/mnist_gan"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/kushrm2803/mnist_gan","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kushrm2803%2Fmnist_gan","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kushrm2803%2Fmnist_gan/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kushrm2803%2Fmnist_gan/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kushrm2803%2Fmnist_gan/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kushrm2803","download_url":"https://codeload.github.com/kushrm2803/mnist_gan/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kushrm2803%2Fmnist_gan/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32589259,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T22:12:39.696Z","status":"ssl_error","status_checked_at":"2026-05-03T22:09:10.534Z","response_time":103,"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":["ann","cnn","deep-learning","keras","mnist","tensorflow"],"created_at":"2024-10-24T14:06:10.838Z","updated_at":"2026-05-03T23:34:11.976Z","avatar_url":"https://github.com/kushrm2803.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MNIST GAN (Generative Adversarial Network)\n\nThis project implements a Generative Adversarial Network (GAN) to generate handwritten digits similar to those in the MNIST dataset. The GAN comprises two main components: a generator that creates new images and a discriminator that evaluates their authenticity. The objective is for the generator to produce images that are indistinguishable from real handwritten digits.\n\n## Dataset\n\n- The project uses the MNIST dataset, which is built into TensorFlow.\n\n## Steps\n\nThe process involves the following steps:\n\n1. **Loading the MNIST dataset** and preprocessing the images.\n2. **Defining the generator and discriminator models.**\n3. **Utilizing a custom training loop** to train the GAN over a specified number of epochs.\n4. During training, **the generator and discriminator compete against each other**, leading to improved performance over time.\n5. **Generating digits** using the trained model.\n\n## Results\n\nHere is an example of an image generated after 500 epochs:\n\n![Image Generated after 500 epochs](image500.png)\n\nIncreasing the number of epochs may yield more realistic digits.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkushrm2803%2Fmnist_gan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkushrm2803%2Fmnist_gan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkushrm2803%2Fmnist_gan/lists"}