{"id":13935037,"url":"https://github.com/sozykin/dlpython_course","last_synced_at":"2025-04-06T01:09:37.599Z","repository":{"id":80682361,"uuid":"75606910","full_name":"sozykin/dlpython_course","owner":"sozykin","description":"Примеры для курса \"Программирование глубоких нейронных сетей на Python\"","archived":false,"fork":false,"pushed_at":"2019-08-06T09:18:36.000Z","size":20613,"stargazers_count":320,"open_issues_count":3,"forks_count":247,"subscribers_count":41,"default_branch":"master","last_synced_at":"2025-03-30T00:08:22.176Z","etag":null,"topics":["deep-learning","deep-learning-tutorial","deep-neural-networks","keras","keras-tensorflow","keras-tutorials","python","tensorflow","tensorflow-tutorials"],"latest_commit_sha":null,"homepage":"https://www.asozykin.ru/courses/nnpython","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/sozykin.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}},"created_at":"2016-12-05T09:00:54.000Z","updated_at":"2025-02-17T05:56:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"2cb8669d-84c7-4d1e-831f-c9f6f120a34c","html_url":"https://github.com/sozykin/dlpython_course","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sozykin%2Fdlpython_course","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sozykin%2Fdlpython_course/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sozykin%2Fdlpython_course/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sozykin%2Fdlpython_course/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sozykin","download_url":"https://codeload.github.com/sozykin/dlpython_course/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247419860,"owners_count":20936012,"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","deep-learning-tutorial","deep-neural-networks","keras","keras-tensorflow","keras-tutorials","python","tensorflow","tensorflow-tutorials"],"created_at":"2024-08-07T23:01:21.965Z","updated_at":"2025-04-06T01:09:37.583Z","avatar_url":"https://github.com/sozykin.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# Примеры программ для курса \"Программирование глубоких нейронных сетей на Python\"\n\n[Страница курса с видеолекциями и практическими заданиями](https://www.asozykin.ru/courses/nnpython).\n\n## Примеры\n\n1. Распознавание рукописных цифр из набора данных [MNIST](http://yann.lecun.com/exdb/mnist/) - `mnist`. Используется полносвязная и сверточная нейронные сети.\n2. Распознавание объектов на изображениях из набора данных [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html) - `cifar10`. Используется сверточная нейронная сеть.\n3. Определение тональности отзывов на фильмы из [IMDB Movie Review Dataset](http://ai.stanford.edu/~amaas/data/sentiment/) - `imdb`. Используется рекуррентная сеть LSTM.\n4. Прогноз стоимости домов для набора данных [Boston Housing](https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html) - `regression`. Пример решения задачи регрессии.\n5. Использование предварительно обученных нейронных сетей - `pretrained_networks`\n6. Сохранение обученной нейронной сети - `saving_models`.\n7. Примеры задач компьютерного зрения - `computer_vision`.\n\n## Необходимое ПО\n\n1. Python 3.\n2. Библиотека глубокого обучения [Keras](https://keras.io/).\n3. Библиотеки  [TensorFlow](https://www.tensorflow.org/) или [Theano](http://deeplearning.net/software/theano/) (используются в качестве вычислительного бекенда для Keras).\n\nИнструкция по установке:\n\n- [Keras и TensorFlow в Anaconda](https://www.asozykin.ru/deep_learning/2017/09/07/Keras-Installation-TensorFlow.html).\n- [Keras и Theano в Anaconda](https://www.asozykin.ru/deep_learning/2016/12/25/Keras-Installation.html).\n\nПримеры тестировались с TensorFlow. При использовании Theano возможны проблемы из-за разных подходов к хранению изображений.\n\n## Благодарности\n\nПри реализации проекта используются средства поддержки, выделенные в качестве гранта на основании конкурса, проведенного Общероссийской общественно-государственной просветительской организации «Российское общество «Знание».\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsozykin%2Fdlpython_course","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsozykin%2Fdlpython_course","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsozykin%2Fdlpython_course/lists"}