{"id":20337919,"url":"https://github.com/gt-ripl/multiagentperception","last_synced_at":"2025-04-11T22:52:20.182Z","repository":{"id":37057502,"uuid":"272565603","full_name":"GT-RIPL/MultiAgentPerception","owner":"GT-RIPL","description":"Official source code to CVPR'20 paper, \"When2com: Multi-Agent Perception via Communication Graph Grouping\"","archived":false,"fork":false,"pushed_at":"2023-07-06T21:14:42.000Z","size":1275,"stargazers_count":59,"open_issues_count":8,"forks_count":12,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-11T22:52:14.442Z","etag":null,"topics":["cvpr2020","deep-learning","multi-agent-systems","multi-view","semantic-segmentation"],"latest_commit_sha":null,"homepage":"https://ycliu93.github.io/projects/multi-agent-perception.html","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GT-RIPL.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}},"created_at":"2020-06-15T23:36:04.000Z","updated_at":"2025-03-21T08:51:27.000Z","dependencies_parsed_at":"2022-07-20T11:32:07.670Z","dependency_job_id":null,"html_url":"https://github.com/GT-RIPL/MultiAgentPerception","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/GT-RIPL%2FMultiAgentPerception","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GT-RIPL%2FMultiAgentPerception/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GT-RIPL%2FMultiAgentPerception/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GT-RIPL%2FMultiAgentPerception/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GT-RIPL","download_url":"https://codeload.github.com/GT-RIPL/MultiAgentPerception/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248492965,"owners_count":21113161,"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":["cvpr2020","deep-learning","multi-agent-systems","multi-view","semantic-segmentation"],"created_at":"2024-11-14T21:10:52.088Z","updated_at":"2025-04-11T22:52:20.147Z","avatar_url":"https://github.com/GT-RIPL.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## When2com: Multi-Agent Perception via Communication Graph Grouping\n\u003cimg src=\"teaser/pytorch-logo-dark.png\" width=\"10%\"\u003e [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) \n\nThis is the PyTorch implementation of our paper: \u003cbr\u003e\n**When2com: Multi-Agent Perception via Communication Graph Grouping**\u003cbr\u003e\n[__***Yen-Cheng Liu***__](https://ycliu93.github.io/), [Junjiao Tian](https://www.linkedin.com/in/junjiao-tian-42b9758a/), [Nathaniel Glaser](https://sites.google.com/view/nathanglaser/), [Zsolt Kira](https://www.cc.gatech.edu/~zk15/)\u003cbr\u003e\nIEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 \u003cbr\u003e\n\n\n[[Paper](http://openaccess.thecvf.com/content_CVPR_2020/papers/Liu_When2com_Multi-Agent_Perception_via_Communication_Graph_Grouping_CVPR_2020_paper.pdf)] [[GitHub](https://github.gatech.edu/RIPL/multi-agent-perception)] [[Project](https://ycliu93.github.io/projects/multi-agent-perception.html)]\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"teaser/1359-teaser.gif\" width=\"50%\"\u003e\n\u003c/p\u003e\n\n## Prerequisites\n- Python 3.6\n- Pytorch 0.4.1\n- Other required packages in `requirement.txt`\n\n\n## Getting started\n### Download and install miniconda \n```\nwget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh\nbash Miniconda3-latest-Linux-x86_64.sh\n```\n\n### Create conda environment\n```\nconda create -n semseg python=3.6\nsource actviate semseg\n```\n\n### Install the required packages\n```\npip install -r requirements.txt\n```\n\n### Download AirSim-MAP dataset and unzip it. \n- Download the zip file you would like to run\n\n[![Alt text](https://ycliu93.github.io/projects/cvpr20_assets/airsim_map.png)](https://gtvault-my.sharepoint.com/:f:/g/personal/yliu3133_gatech_edu/Ett0G1_5YYdBpgojk0uWESgBi95dO79LkbYaKRhlBIkVJQ?e=vdjklb/)\n\n\n### Move the datasets to the dataset path\n```\nmkdir dataset\nmv (dataset folder name) dataset/\n```\n\n### Training \n```\n# [Single-request multi-support] All norm  \npython train.py --config configs/srms-allnorm.yml --gpu=0\n\n# [Multi-request multi-support] when2com model  \npython train.py --config configs/mrms-when2com.yml --gpu=0\n\n```\n\n### Testing \n```\n# [Single-request multi-support] All norm  \npython test.py --config configs/srms-allnorm.yml --model_path \u003cyour trained weights\u003e --gpu=0\n\n# [Multi-request multi-support] when2com model  \npython test.py --config configs/mrms-when2com.yml --model_path \u003cyour trained weights\u003e --gpu=0\n```\n\n## Acknowledgments\n- This work was supported by ONR grant N00014-18-1-2829.\n- This code is built upon the implementation from [Pytorch-semseg](https://github.com/meetshah1995/pytorch-semseg).\n\n## Citation\nIf you find this repository useful, please cite our paper:\n\n```\n@inproceedings{liu2020when2com,\n    title={When2com: Multi-Agent Perception via Communication Graph Grouping},\n    author={Yen-Cheng Liu and Junjiao Tian and Nathaniel Glaser and Zsolt Kira},\n    booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\n    year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgt-ripl%2Fmultiagentperception","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgt-ripl%2Fmultiagentperception","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgt-ripl%2Fmultiagentperception/lists"}