{"id":17153156,"url":"https://github.com/axect/deeponet_template","last_synced_at":"2025-03-24T13:10:43.116Z","repository":{"id":239857635,"uuid":"800402250","full_name":"Axect/DeepONet_Template","owner":"Axect","description":null,"archived":false,"fork":false,"pushed_at":"2024-05-16T09:04:12.000Z","size":15,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-19T22:17:24.938Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Axect.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-14T09:08:50.000Z","updated_at":"2024-09-26T11:10:44.000Z","dependencies_parsed_at":"2024-05-15T20:36:56.604Z","dependency_job_id":null,"html_url":"https://github.com/Axect/DeepONet_Template","commit_stats":null,"previous_names":["axect/deeponet_template"],"tags_count":0,"template":true,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Axect%2FDeepONet_Template","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Axect%2FDeepONet_Template/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Axect%2FDeepONet_Template/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Axect%2FDeepONet_Template/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Axect","download_url":"https://codeload.github.com/Axect/DeepONet_Template/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245276195,"owners_count":20588894,"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":"2024-10-14T21:45:26.576Z","updated_at":"2025-03-24T13:10:43.093Z","avatar_url":"https://github.com/Axect.png","language":"Python","readme":"# DeepONet Template Library\n\nThis is a template library for conducting research on DeepONet, a deep learning architecture for learning operators and solving partial differential equations. The library provides a modular and extensible framework for defining, training, and evaluating DeepONet models.\n\n## Directory Structure\n\nThe template library has the following directory structure:\n\n```\n./\n├── README.md\n├── analyze.py\n├── deeponet\n│   ├── __init__.py\n│   ├── data.py\n│   ├── model.py\n│   ├── train.py\n│   └── utils.py\n├── freeze.sh\n├── kan.sh\n├── requirements.txt\n└── run.py\n```\n\n- `README.md`: This file, providing an overview and documentation of the library.\n- `analyze.py`: A script for analyzing trained models and generating visualizations.\n- `deeponet/`: The main package containing the core components of the library.\n  - `__init__.py`: Package initialization file.\n  - `data.py`: Module for loading and preprocessing data.\n  - `model.py`: Module defining the DeepONet model architectures.\n  - `train.py`: Module for training DeepONet models.\n  - `utils.py`: Module containing utility functions and classes.\n- `freeze.sh`: A shell script for freezing the library's dependencies into `requirements.txt`.\n- `kan.sh`: A shell script for cloning and setting up the Kolmogorov-Arnold Network (KAN) repository.\n- `requirements.txt`: A file listing the library's dependencies.\n- `run.py`: The main script for running experiments and training models.\n\n## Prerequisites\n\n- Python 3.7 or higher\n- Git\n- [uv](https://github.com/astral-sh/uv)\n\n## Installation\n\nTo install the library and its dependencies, follow these steps:\n\n1. Clone the repository:\n   ```\n   git clone https://github.com/Axect/DeepONet_Template\n   ```\n\n2. Navigate to the library directory:\n   ```\n   cd DeepONet_Template\n   ```\n\n3. Set up a virtual environment via uv:\n   ```\n   uv venv\n   uv pip sync requirements.txt\n   source .venv/bin/activate\n   ```\n\n4. (Optional) Run the `kan.sh` script to download efficient-kan (Kolmogorov-Arnold Network):\n   ```\n   sh kan.sh\n   ```\n\n## Usage\n\nTo use the DeepONet template library, follow these steps:\n\n1. Prepare your data:\n   - Organize your data into the appropriate format required by the library.\n   - Modify the `data.py` module to load and preprocess your data.\n\n2. Define your model:\n   - Choose the appropriate DeepONet model architecture from the `model.py` module or create a new one.\n   - Modify the model architecture and hyperparameters as needed.\n\n3. Train your model:\n   - Use the `run.py` script to train your model.\n   - Adjust the training parameters and hyperparameters in the `run.py` script.\n\n4. Analyze and visualize results:\n   - Use the `analyze.py` script to analyze the trained models and generate visualizations.\n   - Customize the analysis and visualization code in `analyze.py` based on your requirements.\n\n5. (Optional) Freeze the dependencies:\n   - If you make changes to the library's dependencies, run the `freeze.sh` script to update the `requirements.txt` file.\n\n## Contributing\n\nContributions to the DeepONet template library are welcome! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request on the GitHub repository.\n\n## License\n\nThis project is licensed under the [MIT License](LICENSE).\n\n## Acknowledgments\n\nThis template library was inspired by various research papers and implementations of [DeepONet](https://github.com/lululxvi/deeponet).\nWe would like to acknowledge the contributors and researchers who have made significant contributions to the field of DeepONet and related areas.\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faxect%2Fdeeponet_template","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faxect%2Fdeeponet_template","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faxect%2Fdeeponet_template/lists"}