{"id":21546969,"url":"https://github.com/lexxai/goit_python_ds_hw_08","last_synced_at":"2026-04-14T04:02:51.258Z","repository":{"id":231796702,"uuid":"760144594","full_name":"lexxai/goit_python_ds_hw_08","owner":"lexxai","description":"Модуль 8. Глибоке навчання. Tensorflow.","archived":false,"fork":false,"pushed_at":"2024-02-21T21:29:48.000Z","size":1425,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-24T09:23:10.093Z","etag":null,"topics":["classification","data-science","matplotlib","minst","numpy","pandas","python","sklearn","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lexxai.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,"roadmap":null,"authors":null,"dei":null}},"created_at":"2024-02-19T21:36:07.000Z","updated_at":"2024-04-06T00:03:50.000Z","dependencies_parsed_at":"2024-04-06T02:22:27.903Z","dependency_job_id":"7cbe188c-ad82-4012-b1a2-01d530f264a2","html_url":"https://github.com/lexxai/goit_python_ds_hw_08","commit_stats":null,"previous_names":["lexxai/goit_python_ds_hw_08"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lexxai%2Fgoit_python_ds_hw_08","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lexxai%2Fgoit_python_ds_hw_08/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lexxai%2Fgoit_python_ds_hw_08/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lexxai%2Fgoit_python_ds_hw_08/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lexxai","download_url":"https://codeload.github.com/lexxai/goit_python_ds_hw_08/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244141582,"owners_count":20404835,"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":["classification","data-science","matplotlib","minst","numpy","pandas","python","sklearn","tensorflow"],"created_at":"2024-11-24T06:13:48.327Z","updated_at":"2026-04-14T04:02:46.221Z","avatar_url":"https://github.com/lexxai.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Модуль 8. Глибоке навчання. Tensorflow.\n\n*З циклу [домашніх завдань Python Data Science](https://github.com/lexxai/goit_python_data_sciense_homework).*\n\n# Домашнє завдання\n\nЗавантажте в гугл колаб [цей](https://drive.google.com/file/d/10-gPf1AeEKXKOlZq9ItbKRo8gtmtNiDV/view) ноутбук. У ньому подано інструкції щодо створення нейронної мережі, що розпізнає рукописні цифри. В даному завданні від вас потрібно зробити наступне:\n\n- Заповнити пропуски у коді.\n- Навчити нейронну мережу.\n- Побудувати необхідні графіки.\n- Знайти втрати мережі.\n- Протестувати роботу мережі на тестових даних.\n- Виведіть метрики якості для кожного класу навченої моделі, використовуючи [classification_report](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html).\n- Зробити висновки.\n\n# Результати\n## Архітектура нейронної мережі\n![nn-shema](nn-shema.jpg)\n\nIL=784, HL1=128, HL2=256, OL=10\n\n## Графік процесу навчання\n![hw08-loss-acc](hw08-loss-acc.png)\n\n## Результати навчання (classification report)\n```\n               precision    recall   f1-score   support\n\n   Number: 0       0.96      0.98      0.97       980\n   Number: 1       0.98      0.98      0.98      1135\n   Number: 2       0.94      0.93      0.94      1032\n   Number: 3       0.92      0.92      0.92      1010\n   Number: 4       0.94      0.94      0.94       982\n   Number: 5       0.93      0.92      0.93       892\n   Number: 6       0.95      0.95      0.95       958\n   Number: 7       0.94      0.94      0.94      1028\n   Number: 8       0.92      0.91      0.92       974\n   Number: 9       0.91      0.92      0.92      1009\n\n    accuracy                           0.94     10000\n   macro avg       0.94      0.94      0.94     10000\nweighted avg       0.94      0.94      0.94     10000\n```\n\n## Результати навчання (Confusion Matrix)\n\n![hw-08-confm](hw-08-confm.png)\n\n## Візуалізація результатів предбачення\n\n![hw-08-pred-imgs](hw-08-pred-imgs.png)\n\n- [goit_python_ds_hw_08.ipynb](goit_python_ds_hw_08.ipynb)\n- [Colab (goit_python_ds_hw_08.ipynb)](https://colab.research.google.com/drive/1FY4LFhix5OiKEXA_et3Zl2P7QWf3JTQk?usp=sharing)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flexxai%2Fgoit_python_ds_hw_08","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flexxai%2Fgoit_python_ds_hw_08","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flexxai%2Fgoit_python_ds_hw_08/lists"}