{"id":15469145,"url":"https://github.com/jmaces/robust-nets","last_synced_at":"2025-04-23T16:11:07.570Z","repository":{"id":139822904,"uuid":"310250382","full_name":"jmaces/robust-nets","owner":"jmaces","description":"Official implementation of the paper \"Solving Inverse Problems With Deep Neural Networks - Robustness Included?\" by M. Genzel, J. Macdonald, and M. März (2020).","archived":false,"fork":false,"pushed_at":"2022-04-12T08:59:58.000Z","size":132,"stargazers_count":28,"open_issues_count":0,"forks_count":5,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-10-09T12:56:20.125Z","etag":null,"topics":["adversarial-examples","deep-learning","fastmri","inverse-problems","neural-networks","robustness","stability"],"latest_commit_sha":null,"homepage":"","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/jmaces.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":"2020-11-05T09:32:34.000Z","updated_at":"2024-04-02T01:43:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"3216d626-63a4-44fd-aea4-e3293494191f","html_url":"https://github.com/jmaces/robust-nets","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/jmaces%2Frobust-nets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jmaces%2Frobust-nets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jmaces%2Frobust-nets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jmaces%2Frobust-nets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jmaces","download_url":"https://codeload.github.com/jmaces/robust-nets/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250468270,"owners_count":21435452,"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":["adversarial-examples","deep-learning","fastmri","inverse-problems","neural-networks","robustness","stability"],"created_at":"2024-10-02T01:52:13.727Z","updated_at":"2025-04-23T16:11:07.565Z","avatar_url":"https://github.com/jmaces.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Solving Inverse Problems With Deep Neural Networks - Robustness Included?\n\n[![GitHub license](https://img.shields.io/github/license/jmaces/robust-nets)](https://github.com/jmaces/robust-nets/blob/master/LICENSE)\n[![code-style black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n[![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)\n[![made-with-pytorch](https://img.shields.io/badge/Made%20with-Pytorch-1f425f.svg)](https://pytorch.org/)\n\nThis repository provides the official implementation of the paper [Solving Inverse Problems With Deep Neural Networks - Robustness Included?](http://arxiv.org/abs/2011.04268) by M. Genzel, J. Macdonald, and M. März (2020).\n\n## Content\n\nThis repository contains subfolders for five experimental scenarios. Each of them is independent of the others.\n\n- [`tvsynth`](tvsynth) : Signal recovery of piecewise constant 1D signals (following a total variation synthesis model) from random Gaussian measurements.\n\n- [`mnist`](mnist) : Signal recovery of approximately piecewise constant 1D signals (vectorized MNIST images) from random Gaussian measurements.\n\n- [`ellipses`](ellipses) : Image reconstruction of 2D phantom ellipses from subsampled Fourier or Radon measurements.\n\n- [`fastmri-radial`](fastmri-radial) : Image reconstruction from multi-coil MRI data with radial line subsampling mask.\n\n- [`fastmri-challenge`](fastmri-challenge) : Image reconstruction from single-coil MRI data with subsampling mask according to the [fastMRI](https://fastmri.org/) challenge (2019).\n\n## Requirements\n\nThe package versions are the ones we used. Other versions might work as well.\n\n`matplotlib` *(v3.1.3)*  \n`numpy` *(v1.18.1)*  \n`pandas` *(v1.0.5)*  \n`piq` *(v0.4.1)*  \n`python` *(v3.8.3)*  \n`pytorch` *(v1.4.0)*  \n`scikit-image` *(v0.16.2)*  \n`torchvision` *(v0.5.0)*  \n`tqdm` *(v4.46.0)*\n\n`h5py` *(v2.10.0)* (only for `fastmri-radial` and `fastmri-challenge`)  \n`odl` *(v0.7.0)* (only for `ellipses`)  \n`pytorch-radon` *(v0.1.3)* (only for `ellipses`)  \n`torch-cg` *(v1.0.1)* (only for `ellipses`)  \n\n## Usage\n\nEach of the individual experiment subfolders contains configuration files as well\nas scripts for preparing the data, for training the neural networks, for obtaining total variation minimization reconstructions, and for finding adversarial perturbations.\n\nThe details are described within in each subfolder.\n\n## Acknowledgements\n\nOur implementation of the U-Net is based on and adapted from https://github.com/mateuszbuda/brain-segmentation-pytorch/.  \nOur implementation of the Tiramisu network is based on and adapted from https://github.com/bfortuner/pytorch_tiramisu/.  \nFor the processing of the fastMRI data we relied on utilty code from https://github.com/facebookresearch/fastMRI.\n\nThank you for making your code available.\n\n## License\n\nThis repository is MIT licensed, as found in the [LICENSE](LICENSE) file.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjmaces%2Frobust-nets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjmaces%2Frobust-nets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjmaces%2Frobust-nets/lists"}