{"id":13730868,"url":"https://github.com/keijiro/Pix2Pix","last_synced_at":"2025-05-08T03:32:09.312Z","repository":{"id":39738135,"uuid":"144393329","full_name":"keijiro/Pix2Pix","owner":"keijiro","description":"Real-time pix2pix implementation with Unity","archived":false,"fork":false,"pushed_at":"2020-05-28T00:03:50.000Z","size":294,"stargazers_count":1035,"open_issues_count":3,"forks_count":132,"subscribers_count":61,"default_branch":"master","last_synced_at":"2024-08-04T02:09:53.789Z","etag":null,"topics":["deep-learning","machine-learning","pix2pix","unity","unity3d"],"latest_commit_sha":null,"homepage":"","language":"C#","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/keijiro.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}},"created_at":"2018-08-11T14:46:54.000Z","updated_at":"2024-07-01T03:44:50.000Z","dependencies_parsed_at":"2022-07-31T23:20:04.020Z","dependency_job_id":null,"html_url":"https://github.com/keijiro/Pix2Pix","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keijiro%2FPix2Pix","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keijiro%2FPix2Pix/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keijiro%2FPix2Pix/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keijiro%2FPix2Pix/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/keijiro","download_url":"https://codeload.github.com/keijiro/Pix2Pix/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224695752,"owners_count":17354473,"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":["deep-learning","machine-learning","pix2pix","unity","unity3d"],"created_at":"2024-08-03T02:01:20.598Z","updated_at":"2024-11-14T21:31:43.449Z","avatar_url":"https://github.com/keijiro.png","language":"C#","funding_links":[],"categories":["C#","unity3d"],"sub_categories":[],"readme":"Pix2Pix for Unity\n=================\n\nThis is an attempt to run [pix2pix] (image-to-image translation with deep\nneural network) in real time with [Unity]. It contains its own implementation\nof an inference engine, so it doesn't require installation of other neural\nnetwork frameworks.\n\n[pix2pix]: https://github.com/phillipi/pix2pix\n[Unity]: https://unity3d.com\n\nSketch Pad demo\n---------------\n\n![screenshot](https://i.imgur.com/aXYYjes.gif)\n![screenshot](https://i.imgur.com/Tb0nYqU.gif)\n\n**Sketch Pad** is a demonstration that resembles the famous [edges2cats] demo\nbut in real time. You can download a pre-built binary from the [Releases] page.\n\n[Demo video](https://vimeo.com/287778343)\n\n[edges2cats]: https://affinelayer.com/pixsrv/\n[Releases]: https://github.com/keijiro/Pix2Pix/releases\n\nSystem requirements\n-------------------\n\n- Unity 2018.1\n- Compute shader capability (DX11, Metal, Vulkan, etc.)\n\nAlthough it's implemented in a platform agnostic fashion, many parts of it are\noptimized for NVIDIA GPU architectures. To run the Sketch Pad demo flawlessly,\nit's highly recomended to use a Windows system with GeForce GTX 1070 or greater.\n\nHow to use a trained model\n--------------------------\n\nThis repository doesn't contain any trained model to save the bandwidth and\nstorage quota. To run the example project on Unity Editor, download the\npre-trained [edges2cats model] and copy it into `Assets/StreamingAssets`.\n\n[edges2cats model]: https://github.com/affinelayer/pix2pix-tensorflow-models/blob/master/edges2cats_AtoB.pict\n\nThis implementation only supports the `.pict` weight data format which is used\nin Christopher Hesse's [interactive demo]. You can pick one of the [pre-trained\nmodels] or train your own model with using [pix2pix-tensorflow]. To export\nweight data from a checkpoint, please see the description in the\n[export-checkpoint.py] script.\n\n[interactive demo]: https://affinelayer.com/pixsrv/\n[pre-trained models]: https://github.com/affinelayer/pix2pix-tensorflow-models\n[pix2pix-tensorflow]: https://github.com/affinelayer/pix2pix-tensorflow\n[export-checkpoint.py]: https://github.com/affinelayer/pix2pix-tensorflow/tree/master/server\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeijiro%2FPix2Pix","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkeijiro%2FPix2Pix","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeijiro%2FPix2Pix/lists"}