{"id":19179021,"url":"https://github.com/drsleep/multi-task-refinenet","last_synced_at":"2025-05-10T02:33:13.935Z","repository":{"id":41371468,"uuid":"170039397","full_name":"DrSleep/multi-task-refinenet","owner":"DrSleep","description":"Multi-Task (Joint Segmentation / Depth / Surface Normas) Real-Time Light-Weight RefineNet","archived":true,"fork":false,"pushed_at":"2020-06-25T00:15:28.000Z","size":47519,"stargazers_count":205,"open_issues_count":5,"forks_count":44,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-03-30T12:31:27.421Z","etag":null,"topics":["asymmetric-annotations","depth-estimation","light-weight-refinenet","multi-task","real-time","semantic-segmentation","surface-normals-estimation"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DrSleep.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-02-10T23:25:37.000Z","updated_at":"2024-12-31T06:41:49.000Z","dependencies_parsed_at":"2022-07-30T07:37:59.645Z","dependency_job_id":null,"html_url":"https://github.com/DrSleep/multi-task-refinenet","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/DrSleep%2Fmulti-task-refinenet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DrSleep%2Fmulti-task-refinenet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DrSleep%2Fmulti-task-refinenet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DrSleep%2Fmulti-task-refinenet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DrSleep","download_url":"https://codeload.github.com/DrSleep/multi-task-refinenet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253354489,"owners_count":21895436,"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":["asymmetric-annotations","depth-estimation","light-weight-refinenet","multi-task","real-time","semantic-segmentation","surface-normals-estimation"],"created_at":"2024-11-09T10:41:51.288Z","updated_at":"2025-05-10T02:33:08.918Z","avatar_url":"https://github.com/DrSleep.png","language":"Jupyter Notebook","readme":"# Real-Time Joint Semantic Segmentation, Depth and Surface Normals Estimation (in PyTorch)\n\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/real-time-joint-semantic-segmentation-and/semantic-segmentation-on-nyu-depth-v2)](https://paperswithcode.com/sota/semantic-segmentation-on-nyu-depth-v2?p=real-time-joint-semantic-segmentation-and)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/real-time-joint-semantic-segmentation-and/real-time-semantic-segmentation-on-nyu-depth-1)](https://paperswithcode.com/sota/real-time-semantic-segmentation-on-nyu-depth-1?p=real-time-joint-semantic-segmentation-and)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/real-time-joint-semantic-segmentation-and/monocular-depth-estimation-on-nyu-depth-v2)](https://paperswithcode.com/sota/monocular-depth-estimation-on-nyu-depth-v2?p=real-time-joint-semantic-segmentation-and)\n\n\nThis repository provides official models from the paper `Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations`, available [here](https://arxiv.org/abs/1809.04766)\n\n```\nReal-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations\nVladimir Nekrasov, Thanuja Dharmasiri, Andrew Spek, Tom Drummond, Chunhua Shen, Ian Reid\nIn ICRA 2019\n```\n\n## Getting Started\n\nFor flawless reproduction of our results, the Ubuntu OS is recommended. The models have been tested using Python 2.7.\n\n### Dependencies\n\n```\npip\ntorch\u003e=0.4.0\n```\nTo install required Python packages, please run `pip install -r requirements.txt` (Python2) - use the flag `-u` for local installation.\nThe given examples can be run with, or without GPU.\n\n## Running examples\n\nFor the ease of reproduction, we have embedded all our examples inside Jupyter notebooks.\n\n### Jupyter Notebooks [Local]\n\nIf all the installation steps have been smoothly executed, you can proceed with running any of the notebooks provided in the `src/notebooks/` folder.\nTo start the Jupyter Notebook server, on your local machine run `jupyter notebook`. This will open a web page inside your browser. If it did not open automatically, find the port number from the command's output and paste it into your browser manually.\nAfter that, navigate to the repository folder and choose any of the examples given.\n\n## More to come\n\nOnce time permits, more things will be added to this repository:\n\n* ~~Training and evaluation examples~~ please refer to this [repository](https://github.com/DrSleep/DenseTorch/tree/master/examples/multitask).\n\n\n\n## More projects to check out\n\n1. This project heavily relies on [Light-Weight RefineNet](https://github.com/DrSleep/light-weight-refinenet)\n\n## License\n\nFor academic usage, this project is licensed under the 2-clause BSD License - see the [LICENSE](LICENSE.md) file for details. For commercial usage, please contact the authors.\n\n## Acknowledgments\n\n* University of Adelaide and Australian Centre for Robotic Vision (ACRV) for making this project happen\n* HPC Phoenix cluster at the University of Adelaide for making the training of the models possible\n* PyTorch developers\n* Yerba mate tea\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrsleep%2Fmulti-task-refinenet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdrsleep%2Fmulti-task-refinenet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrsleep%2Fmulti-task-refinenet/lists"}