{"id":16541258,"url":"https://github.com/anibali/infogan","last_synced_at":"2025-08-09T17:22:32.165Z","repository":{"id":137205740,"uuid":"66177739","full_name":"anibali/infogan","owner":"anibali","description":"An unofficial Torch implementation of InfoGAN","archived":false,"fork":false,"pushed_at":"2017-09-05T02:31:35.000Z","size":132,"stargazers_count":19,"open_issues_count":0,"forks_count":3,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-02-01T15:40:49.716Z","etag":null,"topics":["gan","lua","neural-network","torch7"],"latest_commit_sha":null,"homepage":null,"language":"Lua","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/anibali.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2016-08-21T02:33:47.000Z","updated_at":"2020-11-15T18:52:11.000Z","dependencies_parsed_at":null,"dependency_job_id":"d55a2a1e-dcc0-45c4-97b1-489c077727e6","html_url":"https://github.com/anibali/infogan","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anibali%2Finfogan","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anibali%2Finfogan/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anibali%2Finfogan/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anibali%2Finfogan/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anibali","download_url":"https://codeload.github.com/anibali/infogan/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238663204,"owners_count":19509753,"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":["gan","lua","neural-network","torch7"],"created_at":"2024-10-11T18:54:31.613Z","updated_at":"2025-02-13T13:34:58.292Z","avatar_url":"https://github.com/anibali.png","language":"Lua","readme":"# InfoGAN for Torch\n\nThis is an unofficial Torch implementation of the InfoGAN neural network\narchitecture proposed by Chen et al in their paper [\"InfoGAN: Interpretable\nRepresentation Learning by Information Maximizing Generative Adversarial\nNets\"](http://arxiv.org/abs/1606.03657). The original TensorFlow implementation\ncan be found at https://github.com/openai/InfoGAN.\n\n![Generated MNIST digits varying c_1](images/output_varying_c1.png)\n\n![Generated MNIST digits varying c_2](images/output_varying_c2.png)\n\n## Features\n\n* [x] Implement the InfoGAN network architecture\n* [x] Use variational mutual information maximization for the error calculations\n      (as per the paper)\n* [x] CLI options for tweaking noise inputs and salient variables\n* [x] Deterministic training\n\n## Requirements\n\n* A cuDNN 5 capable NVIDIA graphics card\n* [nvidia-docker](https://github.com/NVIDIA/nvidia-docker)\n\n## Running\n\nBegin by cloning this repository.\n\n```sh\ngit clone https://github.com/anibali/infogan\ncd infogan\n```\n\n**NOTE:** If you are using a Pascal architecture GPU (CUDA 8.0), you will need\nto modify the Dockerfile to build from a CUDA 8.0 base image. Refer to\nhttps://github.com/anibali/infogan/issues/5 for more details. Please make this\nchange before proceeding.\n\nBuild the Docker image which contains Torch and all other required\ndependencies.\n\n```sh\nnvidia-docker build -t infogan-torch .\n```\n\nDownload the MNIST dataset.\n\n```sh\nnvidia-docker run -it --rm --volume=$PWD:/app infogan-torch sh download_mnist.sh\n```\n\nFinally, run the training script.\n\n```sh\nnvidia-docker run -it --rm --volume=$PWD:/app infogan-torch th bin/train_infogan.lua\n```\n\nOutput artifacts will appear in the `out/` directory during training, including\nexamples of fake images generated by the generator network and serialized copies\nof the generator and discriminator networks.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanibali%2Finfogan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanibali%2Finfogan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanibali%2Finfogan/lists"}