{"id":20708285,"url":"https://github.com/vidit98/graphconv","last_synced_at":"2025-04-23T02:17:14.571Z","repository":{"id":78767259,"uuid":"188350458","full_name":"vidit98/graphconv","owner":"vidit98","description":"pytorch implementation of graph convolutions for semantic segmentation on ADE20K dataset","archived":false,"fork":false,"pushed_at":"2019-10-07T15:06:46.000Z","size":7147,"stargazers_count":16,"open_issues_count":2,"forks_count":3,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-23T02:17:07.336Z","etag":null,"topics":["ade20k","deeplearning","graphconvoltution","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/vidit98.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":"2019-05-24T04:09:35.000Z","updated_at":"2023-12-30T12:57:34.000Z","dependencies_parsed_at":"2023-03-27T23:49:29.018Z","dependency_job_id":null,"html_url":"https://github.com/vidit98/graphconv","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/vidit98%2Fgraphconv","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vidit98%2Fgraphconv/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vidit98%2Fgraphconv/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vidit98%2Fgraphconv/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vidit98","download_url":"https://codeload.github.com/vidit98/graphconv/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250354519,"owners_count":21416752,"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":["ade20k","deeplearning","graphconvoltution","pytorch","semantic-segmentation"],"created_at":"2024-11-17T01:30:10.550Z","updated_at":"2025-04-23T02:17:14.559Z","avatar_url":"https://github.com/vidit98.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Introduction\n\n![Semantic Segmentation](https://github.com/vidit98/graphconv/blob/master/ADE_train_00009317_seg.png)\n\n\n\n\nSemantic segmentation is the task of assigning each pixel a class. Many different methods are proposed for the same. This a pytorch implementation of [this](https://papers.nips.cc/paper/8135-beyond-grids-learning-graph-representations-for-visual-recognition.pdf) paper. To know in more detail about the implementation and method refer to [my blog post](https://towardsdatascience.com/visual-recognition-using-graphs-9c446005736e).\n\n## Requirements\n* pytorch 1.1\n* visdom\n* python3\n\n\n## Highlights\n\n* Model can be distributed over many GPUs: pytorch provides the facility to divide data into various GPUs and train the network parallely. But here you can divide the model in various GPUs.\n* Live Data Visualization: You can visualize the training curve live using visdom.\n* Flexible to remove and add GCU units.\n## TO DO\n- [ ] Give flexiblity to use number of GPUs or to run only on CPU, currently model uses 2 GPUs.\n- [ ] Upload checkpoint files\n- [ ] Optimize code\n\n## Training\nDownload data set from [here](https://groups.csail.mit.edu/vision/datasets/ADE20K/). Place all the training images in `data/ADEChallengeData2016/images/training` and ground truth of segmentation in `data/ADEChallengeData2016/annotations/training`.\n\n\nTo put the network to training use the command below. Hyperparameters can be changed by giving inputs via terminal. Please go through the file train.py for knowing about hyperparameters\n\n\n`python3 train.py`\n\nThe network was trained on RTX 2080. It took around 12 hrs to train. Training loss plot is given below.\n![Training Loss](https://github.com/vidit98/graphconv/blob/master/V16epoch120.png)\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvidit98%2Fgraphconv","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvidit98%2Fgraphconv","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvidit98%2Fgraphconv/lists"}