{"id":21714645,"url":"https://github.com/trickygo/jittor-trickysightseeing-landscapeimagegeneration","last_synced_at":"2025-03-20T19:23:42.650Z","repository":{"id":99546940,"uuid":"514222129","full_name":"TrickyGo/jittor-TrickySightseeing-LandscapeImageGeneration","owner":"TrickyGo","description":"第二届计图人工智能竞赛三等奖（Scene Image Generation Track）","archived":false,"fork":false,"pushed_at":"2023-09-11T05:50:10.000Z","size":51,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-25T17:33:14.362Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","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/TrickyGo.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":"2022-07-15T10:06:42.000Z","updated_at":"2025-01-10T06:23:46.000Z","dependencies_parsed_at":null,"dependency_job_id":"8f90a241-440b-4e53-a440-fd8d1fb90fe3","html_url":"https://github.com/TrickyGo/jittor-TrickySightseeing-LandscapeImageGeneration","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/TrickyGo%2Fjittor-TrickySightseeing-LandscapeImageGeneration","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TrickyGo%2Fjittor-TrickySightseeing-LandscapeImageGeneration/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TrickyGo%2Fjittor-TrickySightseeing-LandscapeImageGeneration/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TrickyGo%2Fjittor-TrickySightseeing-LandscapeImageGeneration/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TrickyGo","download_url":"https://codeload.github.com/TrickyGo/jittor-TrickySightseeing-LandscapeImageGeneration/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244676451,"owners_count":20491828,"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":[],"created_at":"2024-11-26T00:37:16.411Z","updated_at":"2025-03-20T19:23:42.645Z","avatar_url":"https://github.com/TrickyGo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# jittor-TrickySightseeing-LandscapeImageGeneration\n# Jittor 草图生成风景比赛\n\n## 简介\n\n本项目包含了TrickySightseeing小队的草图生成风景比赛的代码实现。 获第二届计图人工智能竞赛三等奖（Scene Image Generation Track），10,000 RMB 奖金。\n\n## 安装 \n\n本项目可在 1 张 A100 上运行，batch_size=10。\n\n## 运行环境\n- ubuntu 20.04 LTS\n- python \u003e= 3.7\n- jittor \u003e= 1.3.0\n\n## Part1: Random Sampling Model\n\n### 训练（包含推理）\n单卡训练可运行以下命令：\n```\nbash scripts/train.sh\n```\n在每一个epoch训完后会进行测试集推理。\n\n### 推理\n单卡推理可运行以下命令：\n```\nbash scripts/test.sh\n```\n即可load位于'results/saved_models/'中的预训练模型进行测试，并将测试结果保存至'results/'\n\n## Part2: Part-level Style Transfer Model\n\n### 为风格迁移寻找合适的参考图片（具有相同的标签组）\n首先需要分别为训练集和测试集执行：\n```\npython check_semantics.py\n```\n以分别生成val_semantics_list.data和training_semantics_list.data，包含了图片的标签组信息。\n然后执行：\n```\npython find_match.py\n```\n寻找合适的参考对应关系，保存在match_dict.data中。\n\n### 训练（包含推理）\n单卡训练可运行以下命令：\n```\nbash scripts/train_model_for_transfer.sh\n```\n在每一个epoch训完后会进行测试集推理。\n\n### 推理（风格迁移）\n单卡推理可运行以下命令：\n```\nbash scripts/transfer.sh\n```\n即可load位于'results/saved_models/'中的预训练模型进行风格迁移，并将测试结果保存至'results/'\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrickygo%2Fjittor-trickysightseeing-landscapeimagegeneration","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftrickygo%2Fjittor-trickysightseeing-landscapeimagegeneration","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrickygo%2Fjittor-trickysightseeing-landscapeimagegeneration/lists"}