{"id":13546199,"url":"https://github.com/pfnet-research/chainer-gan-lib","last_synced_at":"2025-10-11T13:16:34.361Z","repository":{"id":22585585,"uuid":"96752066","full_name":"pfnet-research/chainer-gan-lib","owner":"pfnet-research","description":"Chainer implementation of recent GAN variants","archived":false,"fork":false,"pushed_at":"2023-03-24T23:41:30.000Z","size":72925,"stargazers_count":408,"open_issues_count":14,"forks_count":84,"subscribers_count":31,"default_branch":"master","last_synced_at":"2025-05-25T12:06:41.449Z","etag":null,"topics":["dcgan","deep-learning","generative-adversarial-network","wgan-gp"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/pfnet-research.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}},"created_at":"2017-07-10T08:06:02.000Z","updated_at":"2025-03-26T02:44:07.000Z","dependencies_parsed_at":"2024-03-16T16:51:41.992Z","dependency_job_id":null,"html_url":"https://github.com/pfnet-research/chainer-gan-lib","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pfnet-research/chainer-gan-lib","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pfnet-research%2Fchainer-gan-lib","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pfnet-research%2Fchainer-gan-lib/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pfnet-research%2Fchainer-gan-lib/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pfnet-research%2Fchainer-gan-lib/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pfnet-research","download_url":"https://codeload.github.com/pfnet-research/chainer-gan-lib/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pfnet-research%2Fchainer-gan-lib/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279007315,"owners_count":26084280,"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","status":"online","status_checked_at":"2025-10-11T02:00:06.511Z","response_time":55,"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":["dcgan","deep-learning","generative-adversarial-network","wgan-gp"],"created_at":"2024-08-01T12:00:33.830Z","updated_at":"2025-10-11T13:16:34.332Z","avatar_url":"https://github.com/pfnet-research.png","language":"Python","funding_links":[],"categories":["Preferred Networks Research","Python"],"sub_categories":["Services using Chainer"],"readme":"# Chainer-GAN-lib\nThis repository collects chainer implementation of state-of-the-art GAN algorithms.  \nThese codes are evaluated with the _inception score_ on Cifar-10 dataset.  \nNote that our codes are not faithful re-implementation of the original paper.\n\nHow to use\n-------\n\nInstall the requirements first:\n```\npip install -r requirements.txt\n```\nThis implementation has been tested with the following versions.\n```\npython 3.5.2\nchainer 4.0.0\n+ https://github.com/chainer/chainer/pull/3615\n+ https://github.com/chainer/chainer/pull/3581\ncupy 3.0.0\ntensorflow 1.2.0 # only for downloading inception model\nnumpy 1.11.1\n```\nDownload the inception score module forked from [https://github.com/hvy/chainer-inception-score](https://github.com/hvy/chainer-inception-score).\n```\ngit submodule update -i\n```\nDownload the inception model.\n```\ncd common/inception\npython download.py --outfile inception_score.model\n```\nYou can start training with `train.py`.\n\n`python train.py --gpu 0 --algorithm dcgan --out result_dcgan`\n\nPlease see `example.sh` to train other algorithms.\n\nQuantitative evaluation\n-------\n\n| | [Inception](https://arxiv.org/abs/1606.03498) | Inception (Official) | [FID](https://arxiv.org/abs/1706.08500) |\n| ------------- | ------------- | ------------- | ------------- |\n| Real data  | 12.0 | 11.24 | 3.2 (train vs test) |\n| [Progressive](http://research.nvidia.com/publication/2017-10_Progressive-Growing-of)  | 8.5 | 8.8 | 19.1 |\n| [SN-DCGAN](https://drive.google.com/file/d/0B8HZ50DPgR3eSVV6YlF3XzQxSjQ/view?usp=sharing)  | 7.5 | 7.41 | 23.6 |\n| [WGAN-GP](https://arxiv.org/abs/1704.00028)  | 6.8 | 7.86 (ResNet) | 28.2 |\n| [DFM](https://openreview.net/pdf?id=S1X7nhsxl)  | 7.3 | 7.72 | 30.1 |\n| [Cramer GAN](https://arxiv.org/abs/1705.10743) | 6.4 | - | 32.7 |\n| [DRAGAN](https://arxiv.org/abs/1705.07215)  | 7.1 | 6.90 | 31.5 | \n| [DCGAN-vanilla](https://arxiv.org/abs/1511.06434) | 6.7 | 6.16 [WGAN2] 6.99 [DRAGAN] | 34.3 |\n| [minibatch discrimination](https://arxiv.org/abs/1606.03498)  | 7.0 | 6.86 (-L+HA) | 31.3 |\n| [BEGAN](https://arxiv.org/abs/1703.10717)  | 5.4 | 5.62 | 84.0 |\n\nInception scores are calculated by average of 10 evaluation with 5000 samples.\n\nFIDs are calculated with 50000 train dataset and 10000 generated samples.\n\nGenerated images\n-------\n\n- Progressive\n\n![progressive](./images/progressive.png)\n\n- SN-DCGAN\n\n![sndcagn](./images/sndcgan.png)\n\n- WGAN-GP\n\n![wgangp](./images/wgan_gp.png)\n\n- DFM\n\n![dfm](./images/dfm.png)\n\n- Cramer GAN\n\n![cramer](./images/cramer.png)\n\n- DRAGAN\n\n![dragan](./images/dragan.png)\n\n- DCGAN\n\n![dcgan](./images/dcgan.png)\n\n- Minibatch discrimination\n\n![minibatch_dis](./images/minibatch_dis.png)\n\n- BEGAN\n\n![began](./images/began.png)\n\nLicense\n-------\nMIT License. Please see the LICENSE file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpfnet-research%2Fchainer-gan-lib","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpfnet-research%2Fchainer-gan-lib","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpfnet-research%2Fchainer-gan-lib/lists"}