{"id":26134361,"url":"https://github.com/m1dsolo/echocardmae","last_synced_at":"2026-04-18T23:02:11.403Z","repository":{"id":280823694,"uuid":"937844034","full_name":"m1dsolo/EchoCardMAE","owner":"m1dsolo","description":"EchoCardMAE: Video Masked Auto-Encoders Customized for Echocardiography","archived":false,"fork":false,"pushed_at":"2025-05-15T04:24:31.000Z","size":21,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-15T05:20:58.165Z","etag":null,"topics":["camus","deep-learning","echonet","echonet-dynamic","mae","python3","pytorch","videomae"],"latest_commit_sha":null,"homepage":"","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/m1dsolo.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,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-02-24T01:58:52.000Z","updated_at":"2025-05-15T04:24:35.000Z","dependencies_parsed_at":"2025-05-15T05:29:57.133Z","dependency_job_id":null,"html_url":"https://github.com/m1dsolo/EchoCardMAE","commit_stats":null,"previous_names":["m1dsolo/echocardmae"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/m1dsolo/EchoCardMAE","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m1dsolo%2FEchoCardMAE","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m1dsolo%2FEchoCardMAE/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m1dsolo%2FEchoCardMAE/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m1dsolo%2FEchoCardMAE/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/m1dsolo","download_url":"https://codeload.github.com/m1dsolo/EchoCardMAE/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m1dsolo%2FEchoCardMAE/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31987884,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T20:23:30.271Z","status":"ssl_error","status_checked_at":"2026-04-18T20:23:29.375Z","response_time":103,"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":["camus","deep-learning","echonet","echonet-dynamic","mae","python3","pytorch","videomae"],"created_at":"2025-03-11T00:00:14.752Z","updated_at":"2026-04-18T23:02:11.331Z","avatar_url":"https://github.com/m1dsolo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EchoCardMAE: Video Masked Auto-Encoders Customized for Echocardiography\n\n## Introduction\n\n![framework](https://github.com/user-attachments/assets/7b3f0c04-ab75-4038-8efa-c1d92e9eece9)\n\n## Visualization\n\n### Reconstruction\n\nEchoCardMAE reconstruction results on the EchoNet-Dynamic dataset.\n\n\u003cimg src=\"https://github.com/user-attachments/assets/6ee03655-620c-49d7-a92a-e0150c04befd\" width=\"50%\"\u003e\n\n### Segmentation\n\nSegmentation results on the EchoNet-Dynamic and CAMUS dataset.\n\n![echonet-camus-seg](https://github.com/user-attachments/assets/e938ec59-dbc5-4e21-96bd-cafb4dda9b60)\n\n## Installation\n\n```bash\n# remove GIT_LFS_SKIP_SMUDGE=1 if you want to download the pretraining weights\nGIT_LFS_SKIP_SMUDGE=1 git clone https://github.com/m1dsolo/EchoCardMAE.git\ncd EchoCardMAE\nconda create -n EchoCardMAE python=3.10\nconda activate EchoCardMAE\npip install -r requirements.txt\ngit submodule add --depth=1 https://github.com/m1dsolo/yangdl.git yangdl\ncd yangdl\npip install -e .\n```\n\nExperimental environment:\n- PyTorch 2.5.1\n- Python 3.10.15\n- GPU memory 24GB\n\n## Usage\n\n### Data Preparation\n\n1. EchoNet-Dynamic: [Download](https://echonet.github.io/dynamic/index.html#dataset) to `EchoCardMAE/dataset/EchoNet-Dynamic`\n2. CAMUS: [Download](https://humanheart-project.creatis.insa-lyon.fr/database/#collection/6373703d73e9f0047faa1bc8) to `EchoCardMAE/dataset/CAMUS`\n3. HMC-QU: [Download](https://www.kaggle.com/datasets/aysendegerli/hmcqu-dataset) to `EchoCardMAE/dataset/hmcqu-dataset`\n\n### Data preprocessing\n\n1. Ejection fraction (EF) prediction:\n\n```bash\npython -m echonet.avi2npy\n```\n\n2. Segmentation:\n\n```bash\npython -m echonet.avi2edes_npy\n```\n\n### Pre-training\n\nYou can use [pretraining weights](EchoCardMAE.pt) provided by us.\nOr you can pretrain the model by yourself:\n\n```bash\npython pretrain.py\n```\n\n### Fine-tuning\n\n1. EF prediction:\n\n```bash\npython -m echonet.train_ef\npython -m echonet.val_ef\n```\n\n2. Segmentation:\n\n```bash\npython -m echonet.train_seg\n```\n\n## TODO\n\n- [ ] upload the code of CAMUS and HMC-QU\n\n## Citation\n\nTODO\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fm1dsolo%2Fechocardmae","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fm1dsolo%2Fechocardmae","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fm1dsolo%2Fechocardmae/lists"}