{"id":28631115,"url":"https://github.com/zaccharieramzi/tf-fastmri-data","last_synced_at":"2025-06-12T13:10:17.040Z","repository":{"id":42009543,"uuid":"285246424","full_name":"zaccharieramzi/tf-fastmri-data","owner":"zaccharieramzi","description":"TensorFlow data pipelines for the fastMRI dataset","archived":false,"fork":false,"pushed_at":"2022-04-18T20:11:23.000Z","size":105,"stargazers_count":2,"open_issues_count":2,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-21T07:42:57.621Z","etag":null,"topics":["fastmri","fastmri-challenge","fastmri-dataset","tensorflow"],"latest_commit_sha":null,"homepage":"https://fastmri.org/","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/zaccharieramzi.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}},"created_at":"2020-08-05T09:47:44.000Z","updated_at":"2024-11-23T02:19:15.000Z","dependencies_parsed_at":"2022-08-12T02:11:12.683Z","dependency_job_id":null,"html_url":"https://github.com/zaccharieramzi/tf-fastmri-data","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaccharieramzi%2Ftf-fastmri-data","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaccharieramzi%2Ftf-fastmri-data/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaccharieramzi%2Ftf-fastmri-data/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zaccharieramzi%2Ftf-fastmri-data/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zaccharieramzi","download_url":"https://codeload.github.com/zaccharieramzi/tf-fastmri-data/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":255620005,"owners_count":22259867,"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":["fastmri","fastmri-challenge","fastmri-dataset","tensorflow"],"created_at":"2025-06-12T13:10:15.345Z","updated_at":"2025-06-12T13:10:17.015Z","avatar_url":"https://github.com/zaccharieramzi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# tf-fastmri-data\n[![Build Status](https://travis-ci.com/zaccharieramzi/tf-fastmri-data.svg?branch=master)](https://travis-ci.com/zaccharieramzi/tf-fastmri-data)\n\nBuilt around the `tf.data` API, `tf-fastmri-data` offers reliable, unit-tested, datasets for the fastMRI dataset.\n\n## Installation\n\nCurrently, you need to install the package from source:\n\n```\ngit clone https://github.com/zaccharieramzi/tf-fastmri-data.git\ncd tf-fastmri-data\npip install .\n```\n\n## Example use\n\n```python\nfrom tf_fastmri_data.datasets.cartesian import CartesianFastMRIDatasetBuilder\n\ntrain_dataset = CartesianFastMRIDatasetBuilder(path='/path/to/singlecoil_train').preprocessed_ds\n```\n\n## Data\n\nTo download the data, you need to consent to the fastMRI terms listed [here](https://fastmri.med.nyu.edu/).\nAfterwards, you should receive an email with data download links.\n\nYou can then use the environment variable `FASTMRI_DATA_DIR` to indicate where your fastMRI is.\nThis will allow you to not have to specify the path when instantiating a `FastMRIDatasetBuilder`.\n\n## PyTorch\n\nThe PyTorch equivalent of this library is simply the [official fastMRI repository](https://github.com/facebookresearch/fastMRI).\nIn particular, the [data folder](https://github.com/facebookresearch/fastMRI/tree/master/data) is where you find the data utils.\n\n## Benchmark\n\nYou can run the benchmark script with the following command:\n```\nFASTMRI_DATA_DIR=/path/to/fastmri python benchmark.py\n```\n\nCurrently the benchmark gives the following output:\n```\nMulti coil with tfio loading (random slice): 0.369743709564209s per-file.\nSingle coil with tfio loading (random slice): 0.02855397939682007s per-file.\nMulti coil with h5py loading (random slice, without preprocessing): 0.010439331208042165s per-file.\nSingle coil with h5py loading (random slice, without preprocessing): 0.0015996736497735258s per-file.\nSingle coil training with tfio loading: 0.04578723907470703s per-step.\n```\n\nYou can also see the recommendation of TensorBoard regarding the single coil dataset (with a very simple model):\n\n![TensorBoard reco](tensorboard_recommendation.png)\n\n## Citation\n\nIf you use the fastMRI data or this code in your research, please consider citing the fastMRI dataset paper:\n\n```\n@inproceedings{zbontar2018fastMRI,\n  title={{fastMRI}: An Open Dataset and Benchmarks for Accelerated {MRI}},\n  author={Jure Zbontar and Florian Knoll and Anuroop Sriram and Matthew J. Muckley and Mary Bruno and Aaron Defazio and Marc Parente and Krzysztof J. Geras and Joe Katsnelson and Hersh Chandarana and Zizhao Zhang and Michal Drozdzal and Adriana Romero and Michael Rabbat and Pascal Vincent and James Pinkerton and Duo Wang and Nafissa Yakubova and Erich Owens and C. Lawrence Zitnick and Michael P. Recht and Daniel K. Sodickson and Yvonne W. Lui},\n  journal = {ArXiv e-prints},\n  archivePrefix = \"arXiv\",\n  eprint = {1811.08839},\n  year={2018}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzaccharieramzi%2Ftf-fastmri-data","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzaccharieramzi%2Ftf-fastmri-data","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzaccharieramzi%2Ftf-fastmri-data/lists"}