{"id":15601066,"url":"https://github.com/lucidrains/transganformer","last_synced_at":"2025-04-30T16:20:31.721Z","repository":{"id":52985508,"uuid":"346566699","full_name":"lucidrains/transganformer","owner":"lucidrains","description":"Implementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GanFormer and TransGan paper","archived":false,"fork":false,"pushed_at":"2021-04-27T15:14:45.000Z","size":299,"stargazers_count":152,"open_issues_count":5,"forks_count":15,"subscribers_count":16,"default_branch":"main","last_synced_at":"2025-03-30T17:46:13.191Z","etag":null,"topics":["artificial-intelligence","attention-mechanism","deep-learning","generative-adversarial-networks","transformers"],"latest_commit_sha":null,"homepage":"","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/lucidrains.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}},"created_at":"2021-03-11T03:31:10.000Z","updated_at":"2025-01-09T23:57:42.000Z","dependencies_parsed_at":"2022-08-13T02:10:42.943Z","dependency_job_id":null,"html_url":"https://github.com/lucidrains/transganformer","commit_stats":null,"previous_names":[],"tags_count":16,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Ftransganformer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Ftransganformer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Ftransganformer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Ftransganformer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lucidrains","download_url":"https://codeload.github.com/lucidrains/transganformer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251739911,"owners_count":21635946,"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":["artificial-intelligence","attention-mechanism","deep-learning","generative-adversarial-networks","transformers"],"created_at":"2024-10-03T02:13:38.929Z","updated_at":"2025-04-30T16:20:31.695Z","avatar_url":"https://github.com/lucidrains.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## TransGanFormer (wip)\n\nImplementation of TransGanFormer, an all-attention GAN that combines the finding from the recent \u003ca href=\"https://arxiv.org/abs/2103.01209\"\u003eGansFormer\u003c/a\u003e and \u003ca href=\"https://arxiv.org/abs/2102.07074\"\u003eTransGan\u003c/a\u003e paper. It will also contain a bunch of tricks I have picked up building transformers and GANs for the last year or so, including efficient linear attention and pixel level attention.\n\n## Install\n\n```bash\n$ pip install transganformer\n```\n\n## Usage\n\n```bash\n$ transganformer --data ./path/to/data\n```\n\n## Citations\n\n```bibtex\n@misc{jiang2021transgan,\n    title   = {TransGAN: Two Transformers Can Make One Strong GAN}, \n    author  = {Yifan Jiang and Shiyu Chang and Zhangyang Wang},\n    year    = {2021},\n    eprint  = {2102.07074},\n    archivePrefix = {arXiv},\n    primaryClass = {cs.CV}\n}\n```\n\n```bibtex\n@misc{hudson2021generative,\n    title   = {Generative Adversarial Transformers}, \n    author  = {Drew A. Hudson and C. Lawrence Zitnick},\n    year    = {2021},\n    eprint  = {2103.01209},\n    archivePrefix = {arXiv},\n    primaryClass = {cs.CV}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Ftransganformer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flucidrains%2Ftransganformer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Ftransganformer/lists"}