{"id":21001148,"url":"https://github.com/cmdbug/enet","last_synced_at":"2025-04-12T06:37:31.729Z","repository":{"id":112731823,"uuid":"362080462","full_name":"cmdbug/ENet","owner":"cmdbug","description":"🍓 PyTorch版ENet增加PointRend学习笔记。","archived":false,"fork":false,"pushed_at":"2021-04-27T11:05:52.000Z","size":3435,"stargazers_count":5,"open_issues_count":3,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-26T02:02:16.607Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cmdbug.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":"2021-04-27T11:01:25.000Z","updated_at":"2024-05-24T08:26:20.000Z","dependencies_parsed_at":null,"dependency_job_id":"9db12d31-5a48-476c-b772-7d8d8ceeca93","html_url":"https://github.com/cmdbug/ENet","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/cmdbug%2FENet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cmdbug%2FENet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cmdbug%2FENet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cmdbug%2FENet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cmdbug","download_url":"https://codeload.github.com/cmdbug/ENet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248530600,"owners_count":21119590,"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":"2024-11-19T08:13:55.309Z","updated_at":"2025-04-12T06:37:31.721Z","avatar_url":"https://github.com/cmdbug.png","language":"Python","readme":"## :rocket: 编码不易，点个star！ ##\n\n- 原始PyTorchENet代码：https://github.com/davidtvs/PyTorch-ENet\n- 原始PointRend代码来自：https://github.com/facebookresearch/detectron2\n\n#### 该项目主要学习PointRend的使用。\n\n项目中已经加入Tensorboard功能，但在使用PointRend时无法在Tensorboard中加入网络结构图，因为模型改造过程中返回值使用了字典而不是元组，导致Tensorboard不支持。有需要的话可以自行修改成元组形式返回数据。\n\n只测试过camvid数据集，cityscapes数据集未测试。初步测试结果是PointRend功能有起作用，但提升多少没有具体分析过。\n\n\u003e 使用方式\n  args.py 中 USE_POINT_REDN = True 打开 PointRend 功能。\n\n:art: 截图\u003cbr/\u003e\n\n训练过程中的效果，对比最后2张图可以看到PointRend是有起到作用的。\n\u003cdiv\u003e\n\u003cimg width=\"800\" height=\"450\" src=\"./wdoc/ENet_PointRend.png\"/\u003e\n\u003c/div\u003e\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcmdbug%2Fenet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcmdbug%2Fenet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcmdbug%2Fenet/lists"}