{"id":19603913,"url":"https://github.com/divelab/completion","last_synced_at":"2025-04-27T19:32:28.657Z","repository":{"id":107289455,"uuid":"120689529","full_name":"divelab/completion","owner":"divelab","description":null,"archived":false,"fork":false,"pushed_at":"2019-10-09T14:24:43.000Z","size":1638,"stargazers_count":15,"open_issues_count":1,"forks_count":3,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-04-05T02:21:51.512Z","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/divelab.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":"2018-02-08T00:28:15.000Z","updated_at":"2025-03-17T13:42:01.000Z","dependencies_parsed_at":"2023-12-03T09:47:59.199Z","dependency_job_id":null,"html_url":"https://github.com/divelab/completion","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/divelab%2Fcompletion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2Fcompletion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2Fcompletion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/divelab%2Fcompletion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/divelab","download_url":"https://codeload.github.com/divelab/completion/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251195930,"owners_count":21550870,"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":"2024-11-11T09:33:39.408Z","updated_at":"2025-04-27T19:32:28.651Z","avatar_url":"https://github.com/divelab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Adversarial Learning for Multi-Modality Missing Data Completion\n\n![model](./utils/data.jpg)\n\nDeep Adversarial Learning for Multi-Modality Missing Data Completion can be used to generate missing modality using the existing modality. \n\nDetailed information is provided in paper (https://dl.acm.org/citation.cfm?id=3219963).\n\n## Citation\n\nIf using this code, please cite our paper.\n\n```\n@inproceedings{cai2018deep,\n  title={Deep adversarial learning for multi-modality missing data completion},\n  author={Cai, Lei and Wang, Zhengyang and Gao, Hongyang and Shen, Dinggang and Ji, Shuiwang},\n  booktitle={Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery \\\u0026 Data Mining},\n  pages={1158--1166},\n  year={2018},\n  organization={ACM}\n}\n```\n\n## System requirement\n\n#### Programming language\nPython \n\n#### Python Packages\ntensorflow (CPU) or tensorflow-gpu (GPU), numpy, h5py, progressbar, PIL, scipy\n\n## Prepare data\n\nWe use ANDI dataset in our paper. Please download the dataset and process the data following the paper. The processed data shoud be saved in h5 format. Both training and testing h5 file should contains three keys ('label', 'mri', 'pet'). The shape of 'mri' and 'pet' in h5 file should be NxDxHxWxC. In adni dataset, we process the data as D=H=W=64, C=1. The shape of 'label' in h5 file shoud be Nx1.\n\n## Configure the network\n\nAll network hyperparameters are configured in main.py.\n\n#### Training\n\nmax_step: how many iterations or steps to train\n\ntest_step: how many steps to perform a mini test or validation\n\nsave_step: how many steps to save the model\n\nsummary_step: how many steps to save the summary\n\ntrade_off: trade of MSE loss and adversarial loss\n\n#### Data\n\ndata_dir: data directory\n\ntrain_data: h5 file for training\n\nvalid_data: h5 file for validation\n\ntest_data: h5 file for testing\n\nbatch: batch size\n\nchannel: input image channel number\n\nheight, width: height and width of input image\n\n#### Debug\n\nlogdir: where to store log\n\nmodeldir: where to store saved models\n\nsampledir: where to store predicted samples, please add a / at the end for convinience\n\nmodel_name: the name prefix of saved models\n\nreload_step: where to return training\n\ntest_step: which step to test or predict\n\nrandom_seed: random seed for tensorflow\n\n#### Network architecture\n\nnetwork_depth: how deep of the U-Net including the bottom layer\n\nstart_channel_num: the number of channel for the first conv layer\n\n## Training\n\n#### Start training\n\nAfter configure the network, we can start to train. Run\n```\npython main.py\n```\n\n## Acknowledgments\n\nPart of code borrows from [PixelDCL](https://github.com/HongyangGao/PixelDCN). Thanks for their excellent work!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdivelab%2Fcompletion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdivelab%2Fcompletion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdivelab%2Fcompletion/lists"}