{"id":26198385,"url":"https://github.com/hajaarh/malaria_hematie_cnn","last_synced_at":"2026-04-13T14:32:29.676Z","repository":{"id":279121940,"uuid":"935691806","full_name":"Hajaarh/malaria_hematie_cnn","owner":"Hajaarh","description":"Algorithme de réseaux de neurones convolutionnels","archived":false,"fork":false,"pushed_at":"2025-02-24T14:32:38.000Z","size":568,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-12-26T03:55:43.139Z","etag":null,"topics":["numpy","pandas","python","resnet-50","sklearn-library","tensorflow","vgg16"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/Hajaarh.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-02-19T21:26:10.000Z","updated_at":"2025-02-24T22:39:21.000Z","dependencies_parsed_at":"2025-02-23T22:28:54.578Z","dependency_job_id":"3364b000-0f11-417c-8361-d0c3bc526cec","html_url":"https://github.com/Hajaarh/malaria_hematie_cnn","commit_stats":null,"previous_names":["hajaarh/malaria_hematie_cnn"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Hajaarh/malaria_hematie_cnn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hajaarh%2Fmalaria_hematie_cnn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hajaarh%2Fmalaria_hematie_cnn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hajaarh%2Fmalaria_hematie_cnn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hajaarh%2Fmalaria_hematie_cnn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Hajaarh","download_url":"https://codeload.github.com/Hajaarh/malaria_hematie_cnn/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hajaarh%2Fmalaria_hematie_cnn/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31757477,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T13:27:56.013Z","status":"ssl_error","status_checked_at":"2026-04-13T13:21:23.512Z","response_time":93,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["numpy","pandas","python","resnet-50","sklearn-library","tensorflow","vgg16"],"created_at":"2025-03-12T02:52:01.993Z","updated_at":"2026-04-13T14:32:29.651Z","avatar_url":"https://github.com/Hajaarh.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"#  Classification d'Images avec CNN - Détection d'Infections  \n\n##  Introduction  \n\nCe projet porte sur la **classification d’images** à l’aide de **réseaux de neurones convolutifs (CNN)**, dans le but d’identifier si une image appartient à une **classe infectée ou non infectée**. L’objectif est d’entraîner différents modèles de deep learning pour comparer leurs performances et identifier le modèle le plus performant pour cette tâche.  \n\nNous avons travaillé avec **trois approches différentes** :  \n1.  **Un modèle CNN entraîné from scratch** (construit sans modèle pré-entraîné).  \n2.  **Un modèle basé sur VGG16** avec fine-tuning.  \n3.  **Un modèle basé sur ResNet50**, également ajusté pour notre dataset.  \n\nLes modèles ont été entraînés sur un dataset d’images contenant deux classes distinctes, et évalués en fonction de plusieurs métriques de classification :  \n-  **Accuracy** : Précision globale du modèle  \n-  **Precision** : Taux de bonnes prédictions par classe  \n-  **Recall (Sensibilité)** : Capacité à détecter les cas positifs  \n-  **F1-score** : Équilibre entre précision et recall  \n-  **AUC-ROC** : Capacité à distinguer les classes  \n\nLes résultats sont visualisés à l’aide de **matrices de confusion** et de **courbes ROC**, permettant d’analyser la robustesse et la fiabilité de chaque modèle.  \n\nCe projet est une **première approche** du deep learning appliqué à la classification d’images et vise à comprendre **les avantages et inconvénients des architectures CNN pré-entraînées et celles développées from scratch**.  \n\n **Objectif final : choisir le meilleur modèle et optimiser ses performances pour une utilisation future.**  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhajaarh%2Fmalaria_hematie_cnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhajaarh%2Fmalaria_hematie_cnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhajaarh%2Fmalaria_hematie_cnn/lists"}