{"id":19491440,"url":"https://github.com/franco-ruggeri/covid19-detection","last_synced_at":"2025-04-25T19:32:19.285Z","repository":{"id":50138591,"uuid":"261888359","full_name":"franco-ruggeri/covid19-detection","owner":"franco-ruggeri","description":"Explainable detection of COVID-19 from chest X-ray images","archived":false,"fork":false,"pushed_at":"2021-08-24T16:58:16.000Z","size":6423,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-13T04:05:01.407Z","etag":null,"topics":["computer-vision","covid-19","deep-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/franco-ruggeri.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":"2020-05-06T22:02:40.000Z","updated_at":"2024-10-15T21:53:44.000Z","dependencies_parsed_at":"2022-08-30T05:51:56.762Z","dependency_job_id":null,"html_url":"https://github.com/franco-ruggeri/covid19-detection","commit_stats":null,"previous_names":["franco-ruggeri/dd2424-covid19-detection"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/franco-ruggeri%2Fcovid19-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/franco-ruggeri%2Fcovid19-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/franco-ruggeri%2Fcovid19-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/franco-ruggeri%2Fcovid19-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/franco-ruggeri","download_url":"https://codeload.github.com/franco-ruggeri/covid19-detection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250882637,"owners_count":21502341,"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":["computer-vision","covid-19","deep-learning"],"created_at":"2024-11-10T21:16:53.178Z","updated_at":"2025-04-25T19:32:18.307Z","avatar_url":"https://github.com/franco-ruggeri.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Explainable Detection of COVID-19 from Chest X-Ray Images\nThis project is part of the Deep Learning in Data Science course (DD2424) at KTH. The goal is to train a classifier for COVID-19 detection from chest X-ray (CXR) images and boost it with explainability. More information can be found in the [report](https://github.com/franco-ruggeri/dd2424-covid19-detection/blob/master/docs/report.pdf). Also check out our [presentation](https://www.youtube.com/watch?v=c1TNhvAmddE\u0026feature=youtu.be).\n\nThis package provides:\n- An [application](#2-application) with a graphical user interface (GUI). This application can be used to make predictions on your images using trained models.\n- A [suite of tools](#2-command-line-suite) with a command-line interface (CLI). These tools can be used to train and test new models.\n- Several modules with a Keras-like API. These modules can be used in Python code.\n\n# 1. Setup\nThe recommended installation is the following:\n```\nwget https://raw.githubusercontent.com/franco-ruggeri/dd2424-covid19-detection/master/scripts/install.sh -O install.sh\nbash -i install.sh\n```\nFollowing the prompt, you can get a ready-to-use installation that uses the [best models we trained](https://drive.google.com/drive/folders/1x7_xh1xNcuvT8j29y7pTyk_3nrFHNZd2?usp=sharing).\n\nThe package is distributed on [PyPi](https://pypi.org/), so can be installed also with:\n```\npip install covid19-detection\n```\nHowever, in this case you have to provide the trained models to the application. You can decide either to download the [best models we trained](https://drive.google.com/drive/folders/1x7_xh1xNcuvT8j29y7pTyk_3nrFHNZd2?usp=sharing) or to train your own models with the [command-line tools](3-command-line-suite).\n\n## 2. Application\nIf you have done the recommended installation, you can launch the application by searching it among the applications. Otherwise, you can launch it from the terminal:\n```\ncovid19-detector\n```\n\n## 3. Command-line suite\nThe command-line suite is available under the *covid19-detection* command. It provides several subcommands. The list can be retrieved with:\n```\ncovid19-detection -h\n```\n\nMore information about each subcommand can be obtained with:\n```\ncovid19-detection \u003csubcommand\u003e -h\n```\n\n## 4. Package\nYou can import the package in your Python code with:\n```\nimport covid19\n```\n\nThe covid19 package is composed of the following sub-packages:\n- covid19.datasets: contains utilities for generating COVIDx, HAM10000 and for building an input pipeline with tf.data.\n- covid19.models: contains ResNet50 and COVID-Net, two deep convolutional neural networks.\n- covid19.explainers: contains Grad-CAM and IG, two explainable AI methods, with some utilities for plotting the explanations.\n- covid19.layers: contains layers used by models in covid19.models.\n- covid19.metrics: contains utilities for computing and plotting metrics.\n- covid19.gui: contains graphical user interface implemented with [Qt](https://www.qt.io/).\n- covid19.cli: contains command-line interface.\n\nEach subpackage provides interesting modules. For example, you can create a COVID-Net as follows:\n```\nfrom covid19.models import COVIDNet\n\nmodel = COVIDNet(n_classes=3)\n```\n\nFor more information about each class, see the comments.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffranco-ruggeri%2Fcovid19-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffranco-ruggeri%2Fcovid19-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffranco-ruggeri%2Fcovid19-detection/lists"}