{"id":13576063,"url":"https://github.com/tim-learn/GeoNet23_casia_tim","last_synced_at":"2025-04-05T05:30:45.055Z","repository":{"id":208544664,"uuid":"721898273","full_name":"tim-learn/GeoNet23_casia_tim","owner":"tim-learn","description":"1st in the ICCV-2023 GeoUniDA challenge","archived":false,"fork":false,"pushed_at":"2023-11-28T15:01:07.000Z","size":5966,"stargazers_count":5,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-11-05T12:32:57.815Z","etag":null,"topics":[],"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/tim-learn.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":"2023-11-22T02:17:12.000Z","updated_at":"2024-07-04T21:58:10.000Z","dependencies_parsed_at":"2024-11-05T12:31:07.053Z","dependency_job_id":"f43a09f9-007a-43a0-bf68-96de50927699","html_url":"https://github.com/tim-learn/GeoNet23_casia_tim","commit_stats":null,"previous_names":["tim-learn/geonet_unida_track","tim-learn/geonet23_casia_tim"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FGeoNet23_casia_tim","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FGeoNet23_casia_tim/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FGeoNet23_casia_tim/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FGeoNet23_casia_tim/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tim-learn","download_url":"https://codeload.github.com/tim-learn/GeoNet23_casia_tim/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247294068,"owners_count":20915330,"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":"2024-08-01T15:01:06.704Z","updated_at":"2025-04-05T05:30:40.045Z","avatar_url":"https://github.com/tim-learn.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# 1st in the ICCV-2023 GeoUniDA challenge\n\n[[Challenge]](https://geonet-challenge.github.io/ICCV2023/challenge.html) [[Leaderboard]](https://eval.ai/web/challenges/challenge-page/2111/leaderboard/4979) [[Paper]](https://liangjian.xyz/assets/paper/iccvw23.pdf)\n\nTeam: CASIA-TIM (Members: Lijun Sheng, Zhengbo Wang, Jian Liang)\n\n### File structure:\n```\n|–– readme.md\n|–– data_list/\n|   |–– UNIDA/\n|\t|\t|–– usa_train.txt\n|\t|\t|–– asia_train.txt\n|\t|\t|–– asia_test.txt\n|\t|\t|–– test.txt\n|   |–– OBJ/\n|   |–– PLACE/\n|   \n|–– main_unida.py\n|–– main_places.py\n|–– main_imnet.py\n|–– data_list.py\n|–– network.py\n```\n\n### Prerequisites:\n- python == 3.10.6\n- torch ==1.12.0\n- torchvision == 0.13.0\n- numpy, scipy, sklearn, PIL, argparse\n\n### Dataset:\nWe use the dataset provided by the challenge to generate txt files and place them in the data_list folder according to the names of each dataset (i.e., UNIDA, OBJ, PLACE). If you want to run the code, please **modify the absolute paths** in all files under data_list folder.\n\n### Note:\nWe integrate the source model training, model adaptation, and test file generation in single python code. The test file of the source model is saved as source_test.txt, and the test file based on the adaptive model is saved as **target_test.txt**.\n\n### Training:\n\n1. #### GeoUniDA\n```python\npython main_unida.py --dset UNIDA --gpu_id 0 \n```\n\n2. #### GeoImNet\n```python\npython main_imnet.py --dset OBJ --gpu_id 1 \n```\n\n3. #### GeoPlace\n```python\npython main_place.py --dset PLACE --gpu_id 2 \n```\n\n### Citation\n\nIf you find this code useful for your research, please cite our paper\n\n```\n@misc{sheng2023self, \n title={Self-training solutions for the ICCV 2023 GeoNet Challenge}, \n author={Sheng, Lijun and Wang, Zhengbo and Liang, Jian}, \n year={2023}\n}\n```\n\n### Contact\n\n- [**liangjian92@gmail.com**](mailto:liangjian92@gmail.com)\n\n- [lijun.sheng@cripac.ia.ac.cn](mailto:lijun.sheng@cripac.ia.ac.cn)\n\n- [zhengbo.wang@cripac.ia.ac.cn](mailto:zhengbo.wang@cripac.ia.ac.cn)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftim-learn%2FGeoNet23_casia_tim","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftim-learn%2FGeoNet23_casia_tim","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftim-learn%2FGeoNet23_casia_tim/lists"}