{"id":48043418,"url":"https://github.com/ucl-bug/lbs","last_synced_at":"2026-04-04T14:15:56.587Z","repository":{"id":235696862,"uuid":"575152234","full_name":"ucl-bug/lbs","owner":"ucl-bug","description":"A learned version of the Born Series for highly-scattering media","archived":false,"fork":false,"pushed_at":"2023-01-29T19:59:54.000Z","size":1163,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-04-24T09:11:37.373Z","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/ucl-bug.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}},"created_at":"2022-12-06T21:48:22.000Z","updated_at":"2024-04-24T09:11:40.581Z","dependencies_parsed_at":"2024-04-24T09:11:40.294Z","dependency_job_id":"96cf2774-195f-474c-bbd6-60c4a677dca2","html_url":"https://github.com/ucl-bug/lbs","commit_stats":null,"previous_names":["ucl-bug/lbs"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ucl-bug/lbs","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ucl-bug%2Flbs","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ucl-bug%2Flbs/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ucl-bug%2Flbs/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ucl-bug%2Flbs/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ucl-bug","download_url":"https://codeload.github.com/ucl-bug/lbs/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ucl-bug%2Flbs/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31402278,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T10:20:44.708Z","status":"ssl_error","status_checked_at":"2026-04-04T10:20:06.846Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":"2026-04-04T14:15:55.917Z","updated_at":"2026-04-04T14:15:56.573Z","avatar_url":"https://github.com/ucl-bug.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Learned Born Series\n\nThis repository contains the code for the paper\n\n\u003e [A Learned Born Series for Highly-Scattering Media](https://arxiv.org/abs/2212.04948)\n\nThis work presents a method for solving the Helmholtz differential equation using a deep learning approach. We propose a modification to the existing convolutional Born series method to reduce the number of iterations required to solve the equation in highly-scattering media. This is achieved by transforming the linear operator into a non-linear one using a deep learning model. The method is tested on simulated examples, showing improved convergence compared to the original convolutional Born series method.\n\nThis repository can also be installed as a Python package using `pip`, to provide an implementation of the method in the [Flax neural network library](https://github.com/google/flax), as well as a Flax implementation of the Convergent Born Series by [Osnabrugge et al., 2016](https://www.sciencedirect.com/science/article/pii/S0021999116302595).\n\n\u003cbr/\u003e\n\n## Installation\n\nTo install the package, clone the repository and run\n\n```bash\npip install -r requirements.txt\npip install -e .\n```\n\nThis will install the package in editable mode, so that any changes to the code will be reflected in the installed package. From here, you have a `Flax` model of the `bno`. Anywhere you can write\n\n```python\nfrom bno import BNO, WrappedBNO\n```\n\nand use it as a model/layer in your code. The `WrappedBNO` is made specifically for acoustic simulations, and takes care of transforming the output into a complex field.\n\n## Train\n\nTo train the network, run\n\n```bash\npython train.py --model bno\n```\n\nTraining takes about 3/4 days to complete on a single GPU, but you get good results already after a few hours.\nThere are several other arguments that can be passed to the script, which can be found by running\n\n```bash\npython train.py --help\n```\n\n## Test\n\nTo test a network, modify the `TRAIN_IDS` variable with your run. The key is an arbitrary string, say `my_model`, while the value needs to be the run ID of the `wandb` run. Then run\n\n```bash\npython test.py --train_id my_model\n```\n\nTo generate the figures from the paper, run\n\n```bash\npython make_figures --figure example --model my_model\n```\n\nwhere `--figure` can be one of `example`, `iterations_error`, `show_iterations`, `show_pareto`, and `--model`.\n\n\n## Citation\n\n[![arXiv](https://img.shields.io/badge/arXiv-2207.01499-b31b1b.svg?style=flat)](https://arxiv.org/abs/2207.01499)\n\nIf you use this repository in your research, please consider citing it as:\n\n```bibtex\n@article{stanziola2022learned,\n  title={A Learned Born Series for Highly-Scattering Media},\n  author={Stanziola, Antonio and Arridge, Simon and Cox, Ben T and Treeby, Bradley E},\n  journal={arXiv preprint arXiv:2212.04948},\n  year={2022}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fucl-bug%2Flbs","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fucl-bug%2Flbs","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fucl-bug%2Flbs/lists"}