{"id":13797957,"url":"https://github.com/pochih/FCN-pytorch","last_synced_at":"2025-05-13T05:31:29.783Z","repository":{"id":40987149,"uuid":"106667264","full_name":"pochih/FCN-pytorch","owner":"pochih","description":"🚘 Easiest Fully Convolutional Networks","archived":false,"fork":false,"pushed_at":"2023-07-06T21:15:35.000Z","size":61993,"stargazers_count":406,"open_issues_count":28,"forks_count":144,"subscribers_count":11,"default_branch":"master","last_synced_at":"2024-11-18T13:43:48.903Z","etag":null,"topics":["computer-vision","deep-learning","fully-convolutional-networks","pytorch","semantic-segmentation"],"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/pochih.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}},"created_at":"2017-10-12T08:42:10.000Z","updated_at":"2024-11-16T04:53:11.000Z","dependencies_parsed_at":"2024-01-17T23:40:30.964Z","dependency_job_id":"8e18e533-79ee-419c-b188-efb0a9bf1fb3","html_url":"https://github.com/pochih/FCN-pytorch","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/pochih%2FFCN-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pochih%2FFCN-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pochih%2FFCN-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pochih%2FFCN-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pochih","download_url":"https://codeload.github.com/pochih/FCN-pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253883041,"owners_count":21978597,"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":["computer-vision","deep-learning","fully-convolutional-networks","pytorch","semantic-segmentation"],"created_at":"2024-08-04T00:00:36.958Z","updated_at":"2025-05-13T05:31:27.940Z","avatar_url":"https://github.com/pochih.png","language":"Python","funding_links":[],"categories":["State-Of-The-Art (SOTA) methods of Semantic Segmentation"],"sub_categories":["Variants"],"readme":"[![Open Source Love](https://badges.frapsoft.com/os/v1/open-source-150x25.png?v=103)](https://github.com/ellerbrock/open-source-badges/)\n\n## 🚘 The easiest implementation of fully convolutional networks\n\n- Task: __semantic segmentation__, it's a very important task for automated driving\n\n- The model is based on CVPR '15 best paper honorable mentioned [Fully Convolutional Networks for Semantic Segmentation](https://arxiv.org/abs/1411.4038)\n\n## Results\n### Trials\n\u003cimg align='center' style=\"border-color:gray;border-width:2px;border-style:dashed\"   src='result/trials.png' padding='5px' height=\"150px\"\u003e\u003c/img\u003e\n\n### Training Procedures\n\u003cimg align='center' style=\"border-color:gray;border-width:2px;border-style:dashed\"   src='result/result.gif' padding='5px' height=\"150px\"\u003e\u003c/img\u003e\n\n\n## Performance\n\nI train with two popular benchmark dataset: CamVid and Cityscapes\n\n|dataset|n_class|pixel accuracy|\n|---|---|---\n|Cityscapes|20|96%\n|CamVid|32|93%\n\n## Training\n\n### Install packages\n```bash\npip3 install -r requirements.txt\n```\n\nand download pytorch 0.2.0 from [pytorch.org](pytorch.org)\n\nand download [CamVid](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/) dataset (recommended) or [Cityscapes](https://www.cityscapes-dataset.com/) dataset\n\n### Run the code\n- default dataset is CamVid\n\ncreate a directory named \"CamVid\", and put data into it, then run python codes:\n```python\npython3 python/CamVid_utils.py \npython3 python/train.py CamVid\n```\n\n- or train with CityScapes\n\ncreate a directory named \"CityScapes\", and put data into it, then run python codes:\n```python\npython3 python/CityScapes_utils.py \npython3 python/train.py CityScapes\n```\n\n## Author\nPo-Chih Huang / [@pochih](https://pochih.github.io/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpochih%2FFCN-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpochih%2FFCN-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpochih%2FFCN-pytorch/lists"}