{"id":20602071,"url":"https://github.com/bessouat40/python-ai-explainability","last_synced_at":"2025-03-06T16:21:46.881Z","repository":{"id":211555336,"uuid":"729431659","full_name":"Bessouat40/python-ai-explainability","owner":"Bessouat40","description":"A python project to find anomaly in an Xray image.","archived":false,"fork":false,"pushed_at":"2024-01-05T17:35:13.000Z","size":57040,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-17T01:49:00.640Z","etag":null,"topics":["deep-learning","explainable-ai","health","python","tensorflow"],"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/Bessouat40.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}},"created_at":"2023-12-09T07:52:21.000Z","updated_at":"2024-12-17T07:35:02.000Z","dependencies_parsed_at":"2024-01-05T18:49:27.154Z","dependency_job_id":null,"html_url":"https://github.com/Bessouat40/python-ai-explainability","commit_stats":null,"previous_names":["bessouat40/unsupervised-image-anomaly-detection","bessouat40/python-ai-explainability"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bessouat40%2Fpython-ai-explainability","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bessouat40%2Fpython-ai-explainability/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bessouat40%2Fpython-ai-explainability/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bessouat40%2Fpython-ai-explainability/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Bessouat40","download_url":"https://codeload.github.com/Bessouat40/python-ai-explainability/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242241419,"owners_count":20095370,"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":["deep-learning","explainable-ai","health","python","tensorflow"],"created_at":"2024-11-16T09:12:45.333Z","updated_at":"2025-03-06T16:21:46.861Z","avatar_url":"https://github.com/Bessouat40.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# python AI explainability\n\nA python project to find anomaly in an Xray image.\n\nThe aim is detect pneumonia in a thorax radiography and explain AI decision.\n\n**_Training data source :_**\n[database link](https://www.kaggle.com/datasets/tolgadincer/labeled-chest-xray-images)\n\n## Model\n\nI use a `VGG16` model.\n\n## M1 use\n\nYou need to create a conda environment to increase your training performances :\n\n```bash\nsource ~/.zshrc\nconda create -n tf_m1 python=3.11\nconda activate tf_m1\nconda install -c apple tensorflow-deps\npip install tensorflow-macos\npip install tensorflow-metal\n```\n\n## Training\n\nFirst create `.env` file :\n\n```bash\nmv .env.example .env\n```\n\nThen fill `.env` file with your values.\n\nIn your conda env :\n\n```bash\npython train.py\n```\n\n## Training results with test set\n\n```bash\n-------------------- Dataset Summary --------------------\n\nNumber of train images :  4684\n\n\nNumber of test images :  586\n\n\nNumber of validation images :  586\n\n\nShape of each images :  (224, 224, 3)\n---------------------------------------------------------\n\nloss: 0.0611 - accuracy: 0.9795\n```\n\n## Results\n\n![output](./media/output.png)\n![output2](./media/output2.png)\n\n## Tensorboard\n\n**_Source :_**\n[tensorboard-doc](https://www.tensorflow.org/tensorboard/get_started?hl=fr)\n\n### For python notebook\n\n```python\n%load_ext tensorboard\n%tensorboard --logdir logs/fit\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbessouat40%2Fpython-ai-explainability","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbessouat40%2Fpython-ai-explainability","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbessouat40%2Fpython-ai-explainability/lists"}