{"id":19787910,"url":"https://github.com/muhammadshavaiz/gan-digit-generator","last_synced_at":"2026-06-09T03:36:55.514Z","repository":{"id":240562668,"uuid":"802969041","full_name":"MuhammadShavaiz/GAN-Digit-Generator","owner":"MuhammadShavaiz","description":"This PyTorch-based GAN generates MNIST-like handwritten digits. It features a generator with transposed convolutions to create 28x28 images from noise and a convolutional discriminator to classify images as real or fake. The model trains adversarially using standard GAN loss to improve both generator and discriminator performance. ","archived":false,"fork":false,"pushed_at":"2024-08-31T13:52:25.000Z","size":1926,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-11T03:44:55.652Z","etag":null,"topics":["convolutional-neural-networks","gan","mnist"],"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/MuhammadShavaiz.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":"2024-05-19T18:38:03.000Z","updated_at":"2024-09-02T16:03:37.000Z","dependencies_parsed_at":null,"dependency_job_id":"774e8afd-9da9-4a30-a664-5cd1bb63d581","html_url":"https://github.com/MuhammadShavaiz/GAN-Digit-Generator","commit_stats":null,"previous_names":["muhammadshavaiz/gan-digit-generator"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MuhammadShavaiz%2FGAN-Digit-Generator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MuhammadShavaiz%2FGAN-Digit-Generator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MuhammadShavaiz%2FGAN-Digit-Generator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MuhammadShavaiz%2FGAN-Digit-Generator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MuhammadShavaiz","download_url":"https://codeload.github.com/MuhammadShavaiz/GAN-Digit-Generator/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241121296,"owners_count":19913249,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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","gan","mnist"],"created_at":"2024-11-12T06:25:03.293Z","updated_at":"2026-06-09T03:36:50.464Z","avatar_url":"https://github.com/MuhammadShavaiz.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GAN Digit Generator\n\nThis repository contains a Generative Adversarial Network (GAN) implementation using PyTorch to generate handwritten digit images similar to those in the MNIST dataset.\n\n## Overview\n\nThe GAN model consists of a generator and a discriminator, trained adversarially. The generator creates digit images from random noise, while the discriminator attempts to distinguish between real MNIST digits and generated ones. \n\n## Model Architecture\n\n- **Generator:** A simple feedforward network with transposed convolutional layers to upscale random noise into a 28x28 grayscale digit image.\n- **Discriminator:** A convolutional network that classifies 28x28 images as real or fake.\n\n## Training\n\nThe training process involves iteratively updating the generator and discriminator using a standard GAN loss. The generator learns to produce increasingly realistic digits, while the discriminator improves its ability to differentiate between real and generated images.\n\n## Results\n\nAfter training, the generator can produce realistic-looking digit images, showcasing the effectiveness of the GAN model.\n\n## Usage\n\nTo generate new digits, simply run the provided script and observe the generated outputs saved in the specified directory.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmuhammadshavaiz%2Fgan-digit-generator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmuhammadshavaiz%2Fgan-digit-generator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmuhammadshavaiz%2Fgan-digit-generator/lists"}