{"id":25582470,"url":"https://github.com/atharvaaalok/geosimilarity","last_synced_at":"2026-04-02T13:30:16.200Z","repository":{"id":276251069,"uuid":"928696923","full_name":"atharvaaalok/geosimilarity","owner":"atharvaaalok","description":"Differentiable curve and surface similarity measures.","archived":false,"fork":false,"pushed_at":"2025-02-07T05:05:08.000Z","size":0,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-07T06:19:17.727Z","etag":null,"topics":["autograd","curve-fitting","curves","differentiable-optimization","geometric-deep-learning","pytorch","shape-matching","similarity-measures","surface-fitting","surfaces"],"latest_commit_sha":null,"homepage":"","language":null,"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/atharvaaalok.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":"2025-02-07T04:24:34.000Z","updated_at":"2025-02-07T05:08:22.000Z","dependencies_parsed_at":"2025-02-07T06:29:25.030Z","dependency_job_id":null,"html_url":"https://github.com/atharvaaalok/geosimilarity","commit_stats":null,"previous_names":["atharvaaalok/geosimilarity"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharvaaalok%2Fgeosimilarity","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharvaaalok%2Fgeosimilarity/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharvaaalok%2Fgeosimilarity/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharvaaalok%2Fgeosimilarity/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/atharvaaalok","download_url":"https://codeload.github.com/atharvaaalok/geosimilarity/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239958315,"owners_count":19724927,"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":["autograd","curve-fitting","curves","differentiable-optimization","geometric-deep-learning","pytorch","shape-matching","similarity-measures","surface-fitting","surfaces"],"created_at":"2025-02-21T05:16:33.759Z","updated_at":"2026-04-02T13:30:16.125Z","avatar_url":"https://github.com/atharvaaalok.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n    \u003cimg alt=\"GeoSimilarity Logo with text on the side.\" src=\"https://raw.githubusercontent.com/atharvaaalok/geosimilarity/refs/heads/main/docs/assets/logos/logo_with_text_inside.svg\" height=\"300px\"\u003e\n\u003c/div\u003e\n\nGeoSimilarity is a differentiable curve and surface similarity loss function library.\n\nIt is built on top of [PyTorch](https://github.com/pytorch/pytorch) and is designed with\nmodularity and extensibility in mind.\n\n\u003e [!NOTE]  \n\u003e We are in the very early stages of development and are inviting domain experts for collaboration.\n\u003e The usage examples below are stand-ins for future api.\n\nFor a flavor of the documentation please refer:\n[Documentation Webpage](https://atharvaaalok.github.io/geosimilarity/)\n\n\n## Basic Usage\nGiven a candidate curve $Xc$ and a target curve $Xt$ we can measure the similarity using a given\nmeasure as follows:\n```python\nimport torch\nimport geosimilarity as gs\n\nXc = torch.randn(10, 2, requires_grad = True)\nXt = torch.randn(10, 2)\n\n# Define a loss object and compute the similarity between curves\nloss_fn = gs.MSELoss()\nloss = loss_fn(Xc, Xt)\n\n# To modify Xc to fit the target use autograd capacity for gradient stepping\nloss.backward()\n```\n\n\n## Inviting Collaborators\nWe are in the very early stages of development are are inviting collaborators for:\n- **Code Optimization:** Benchmark your results and show a clear improvement.\n- **Novel Loss Functions:** Developing new curve/surface/point cloud similarity measures.\n- **Testing:** Incorporating testing codes.\n- **Improving Documentation:** Improving doc-string clarity and including doc tests. Also for\n  improving the documentation website and adding explanations of similarity measures.\n\nWe'll use [Github issues](https://github.com/atharvaaalok/geosimilarity/issues) for tracking pull\nrequests and bugs.\n\n\n## License\nDistributed under the [MIT License](License).\n\n\n## Project Plan:\n- [x] Create first loss function. Mean Squared Error (MSE).\n- [x] Generate proper documentation.\n    - [x] Proper docstrings. Follow Google python coding style guide.\n    - [x] Take inspiration from pytorch.\n    - [x] Use math equations.\n    - [x] Use type annotations.\n- [x] Add .gitignore file.\n- [x] Add testing code.\n    - [x] Use linear splines. Create spline generator function.\n    - [x] Create automated training function.\n    - [x] Create plot function. Parameterized and Target shape comparison.\n    - [x] Generate a bunch of target shapes. Use SVGs.\n- [ ] Create documentation first cut using MyST markdown.\n    - [x] Create motivation/introduction.\n    - [ ] Include function docstrings in the documentation.\n    - [x] Launch web page for documentation using github pages.\n- [x] Add license.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatharvaaalok%2Fgeosimilarity","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fatharvaaalok%2Fgeosimilarity","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatharvaaalok%2Fgeosimilarity/lists"}