{"id":13869854,"url":"https://github.com/Rose-STL-Lab/ECCO","last_synced_at":"2025-07-15T18:32:15.314Z","repository":{"id":114949162,"uuid":"341983497","full_name":"Rose-STL-Lab/ECCO","owner":"Rose-STL-Lab","description":null,"archived":false,"fork":false,"pushed_at":"2022-01-05T05:53:11.000Z","size":577,"stargazers_count":52,"open_issues_count":0,"forks_count":4,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-11-18T02:03:39.565Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/Rose-STL-Lab.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}},"created_at":"2021-02-24T17:41:26.000Z","updated_at":"2024-11-01T12:22:43.000Z","dependencies_parsed_at":null,"dependency_job_id":"d6313550-38ac-4048-be66-f11db391fc1d","html_url":"https://github.com/Rose-STL-Lab/ECCO","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/Rose-STL-Lab%2FECCO","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Rose-STL-Lab%2FECCO/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Rose-STL-Lab%2FECCO/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Rose-STL-Lab%2FECCO/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Rose-STL-Lab","download_url":"https://codeload.github.com/Rose-STL-Lab/ECCO/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226062923,"owners_count":17567924,"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":"2024-08-05T20:01:19.802Z","updated_at":"2024-11-23T15:32:08.636Z","avatar_url":"https://github.com/Rose-STL-Lab.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Trajectory Prediction using Equivariant Continuous Convolution (ECCO)\n\nThis is the codebase for the ICLR 2021 paper [Trajectory Prediction using Equivariant Continuous Convolution](https://arxiv.org/abs/2010.11344), by Robin Walters, Jinxi Li and Rose Yu.\n\n![Thumbnail](no_title_thumbnail.png)\n\n## Installation\n\nThis codebase is trained on Python 3.6.6+. For the usage of argoverse dataset, [argoverse-api](https://github.com/argoai/argoverse-api) is required. We recommand the reader to follow their guide to install the complete api and datasets. Other requirements include:\n- numpy\u003e=1.18.3\n- pandas\u003e=1.0.3\n- torch==1.5.0\n\nDependency can be installed using the following command:\n```bash\npip install -r requirements.txt\n```\n\n## Data Preparation\n\nOriginal data could be downloaded from [argoverse](https://www.argoverse.org/data.html). To generate the training and validation data\n1. Set the path to `argoverse_forecasting` in `datasets/preprocess_data.py` scripts.\n2. Run the script\n```bash\npython preprocess_data.py\n```\nThe data will be stored in `path/to/argoverse_forecasting/train(val)/lane_data`.\n\n## Data Download\n\nIf you want to skip the data generation part, the link to preprocessed data will be provided soon.\n\n## Model Training and Evaluation\n\nHere are commands to train the model. The evaluation will be provided after the model is trained. \n\nFor \u003cimg src=\"https://render.githubusercontent.com/render/math?math=\\rho_1\"\u003e-ECCO, run the following command\n```bash\npython train.py --dataset_path /path/to/argoverse_forecasting/ --rho1 --model_name rho_1_ecco --train --evaluation\n```\n\nFor \u003cimg src=\"https://render.githubusercontent.com/render/math?math=\\rho_{reg}\"\u003e-ECCO, run the following command\n```bash\npython train.py --dataset_path /path/to/argoverse_forecasting/ --rho-reg --model_name rho_1_ecco --train --evaluation\n```\n\nFor the baseline evaluation, you can refer to [Argoverse Official Baseline](https://github.com/jagjeet-singh/argoverse-forecasting). Note: the evaluation of the constant velocity is evaluated on the validation set (filtered out the scenes with car number greater than 60) with the velocity at final timestamp as the constant velocity. \n\n## Citation\n\nIf you find this repository useful in your research, please cite our paper:\n```\n@article{Walters2021ECCO,\n  title={Trajectory Prediction using Equivariant Continuous Convolution},\n  author={Robin Walters and Jinxi Li and Rose Yu},\n  journal={International Conference on Learning Representations},\n  year={2021},\n}\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRose-STL-Lab%2FECCO","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FRose-STL-Lab%2FECCO","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRose-STL-Lab%2FECCO/lists"}