{"id":15637473,"url":"https://github.com/adgaudio/o-medal","last_synced_at":"2025-04-30T06:08:08.414Z","repository":{"id":141771792,"uuid":"168740799","full_name":"adgaudio/O-MedAL","owner":"adgaudio","description":"O-MedAL: Online Active Deep Learning for Medical Image Analysis.  This repo contains code for the paper.","archived":false,"fork":false,"pushed_at":"2022-03-20T23:06:46.000Z","size":2773,"stargazers_count":18,"open_issues_count":1,"forks_count":12,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-30T06:08:02.337Z","etag":null,"topics":["active-learning","deep-learning","diabetic-retinopathy-detection","machine-learning","medical-image-analysis","online-learning"],"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/adgaudio.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}},"created_at":"2019-02-01T18:17:19.000Z","updated_at":"2024-03-14T00:59:17.000Z","dependencies_parsed_at":"2023-10-20T16:20:54.441Z","dependency_job_id":null,"html_url":"https://github.com/adgaudio/O-MedAL","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/adgaudio%2FO-MedAL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adgaudio%2FO-MedAL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adgaudio%2FO-MedAL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adgaudio%2FO-MedAL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adgaudio","download_url":"https://codeload.github.com/adgaudio/O-MedAL/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251651233,"owners_count":21621716,"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":["active-learning","deep-learning","diabetic-retinopathy-detection","machine-learning","medical-image-analysis","online-learning"],"created_at":"2024-10-03T11:11:46.433Z","updated_at":"2025-04-30T06:08:08.382Z","avatar_url":"https://github.com/adgaudio.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# O-MedAL: Online Active Deep Learning for Medical Image Analysis\n\nCode for the paper, written with pytorch.\n\n[on arXiv](https://arxiv.org/abs/1908.10508)\n\n[on Wiley Journal of Data Mining and Knowledge Discovery](https://wires.onlinelibrary.wiley.com/doi/abs/10.1002/widm.1353)\n\n\n## Setup\n\nGit clone the repo, and navigate your shell to the root of the repo.\n\nDownload the Messidor dataset to ./data/messidor/\n\n    $ ls data/messidor\n    Annotation_Base11.csv  Annotation_Base14.csv  Annotation_Base23.csv  Annotation_Base32.csv  Base11  Base14  Base23  Base32\n    Annotation_Base12.csv  Annotation_Base21.csv  Annotation_Base24.csv  Annotation_Base33.csv  Base12  Base21  Base24  Base33\n    Annotation_Base13.csv  Annotation_Base22.csv  Annotation_Base31.csv  Annotation_Base34.csv  Base13  Base22  Base31  Base34\n\nLink your ~/.torch to ./data/torch (avoid downloading pre-trained if you don't need to)\n\n    $ ln -sr ~/.torch ./data/torch\n\nInstall missing python requirements (if necessary)\n\n    $ cat ./requirements.txt\n\nYou should have a gpu on the machine too!  Check with:\n\n    $ nvidia-smi\n\n\n## Usage\n\nFrom the root of this repo, type:\n\n    python -m medal OnlineMedalResnet18BinaryClassifier --run-id test -h\n    python -m medal -h\n\n## The code structure:\n\n  - `medal/model_configs/medal.py` - **the primary source code of\n    interest for this paper.**\n\n  - `medal/model_configs` - contains the collection of model, loss\n    function, default hyperparameters, data loader, etc.  Note that any\n    class variables defined here are magically exposed to the\n    commandline, which is very handy for quick experimentation :)\n\n  - `medal/datasets.py` - the pytorch DataSet for Messidor\n\n  - `medal/models` - contains some simple pytorch model files\n\n## Reproducibility\n\nThe experiments over values of p used to produce the final online\nmedal results is `./bin/reproduce_paper_results.sh`.  You may need to\njust run the \"python -m ...\" bit.  Sorry if this is confusing.\n\nAlso keep in mind if reproducing that we fixed Messidor errata for the\nonline portion of these results, as mentioned in the paper.\n\nI can create a separate GitHub repo to share about 100mb of precisely\ndetailed log files and post-analysis data.  If there is interest for\nthis, please open an issue.\n\nI created a git tag to synchronize the code with published version on\narXiv.\n\n## Questions?\n\nPlease feel free to open an issue or send me an email.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadgaudio%2Fo-medal","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadgaudio%2Fo-medal","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadgaudio%2Fo-medal/lists"}