{"id":13624699,"url":"https://github.com/oreilly-japan/deep-learning-from-scratch-3","last_synced_at":"2025-05-16T11:06:13.440Z","repository":{"id":42187718,"uuid":"217454360","full_name":"oreilly-japan/deep-learning-from-scratch-3","owner":"oreilly-japan","description":"『ゼロから作る Deep Learning ❸』(O'Reilly Japan, 2020)","archived":false,"fork":false,"pushed_at":"2024-05-27T09:55:12.000Z","size":14875,"stargazers_count":789,"open_issues_count":14,"forks_count":309,"subscribers_count":36,"default_branch":"master","last_synced_at":"2025-05-12T04:59:07.601Z","etag":null,"topics":["autograd","automatic-differentiation","deep-learning","gpu","nueral-networks","python"],"latest_commit_sha":null,"homepage":"","language":"Python","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/oreilly-japan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE.md","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},"funding":{"github":["koki0702"],"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"lfx_crowdfunding":null,"custom":null}},"created_at":"2019-10-25T04:59:43.000Z","updated_at":"2025-05-04T23:04:27.000Z","dependencies_parsed_at":"2024-01-14T06:53:42.382Z","dependency_job_id":"1fe33442-0dc6-4c19-9034-3bebab790026","html_url":"https://github.com/oreilly-japan/deep-learning-from-scratch-3","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/oreilly-japan%2Fdeep-learning-from-scratch-3","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oreilly-japan%2Fdeep-learning-from-scratch-3/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oreilly-japan%2Fdeep-learning-from-scratch-3/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/oreilly-japan%2Fdeep-learning-from-scratch-3/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/oreilly-japan","download_url":"https://codeload.github.com/oreilly-japan/deep-learning-from-scratch-3/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254518383,"owners_count":22084374,"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":["autograd","automatic-differentiation","deep-learning","gpu","nueral-networks","python"],"created_at":"2024-08-01T21:01:45.322Z","updated_at":"2025-05-16T11:06:08.432Z","avatar_url":"https://github.com/oreilly-japan.png","language":"Python","funding_links":["https://github.com/sponsors/koki0702"],"categories":["Python"],"sub_categories":[],"readme":"\u003cp\u003e\n\u003ca href=\"https://www.amazon.co.jp/dp/4873119065/ref=cm_sw_r_tw_dp_U_x_KiA1Eb39SW14Q\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/deep-learning-from-scratch-3.png\" height=\"250\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n## 本書概要\n\n本書では「DeZero」というディープラーニングのフレームワークを作ります。DeZeroは本書オリジナルのフレームワークです。最小限のコードで、フレームワークのモダンな機能を実現します。本書では、この小さな——それでいて十分にパワフルな——フレームワークを、全部で60のステップで完成させます。それによって、PyTorch、TensorFlow、Chainerなどの現代のフレームワークに通じる深い知識を養います。\n\n\n\u003cp\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/dezero_logo.png\" width=\"400px\" \u003c/p\u003e\n\n\n\u003cp\u003e\n  \u003ca href=\"https://pypi.python.org/pypi/dezero\"\u003e\u003cimg\n\t\talt=\"pypi\"\n\t\tsrc=\"https://img.shields.io/pypi/v/dezero.svg\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/oreilly-japan/deep-learning-from-scratch-3/blob/master/LICENSE.md\"\u003e\u003cimg\n\t\talt=\"MIT License\"\n\t\tsrc=\"http://img.shields.io/badge/license-MIT-blue.svg\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://travis-ci.org/oreilly-japan/deep-learning-from-scratch-3\"\u003e\u003cimg\n\t\talt=\"Build Status\"\n\t\tsrc=\"https://travis-ci.org/oreilly-japan/deep-learning-from-scratch-3.svg?branch=master\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n## ニュース\n\u003ca href=\"https://koki0702.github.io/dezero-book/\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/koki0702/koki0702.github.io/master/dezero-book/images/summary_ja.png\" height=\"150px\"\u003e\u003c/a\u003e\n\n【試し読み】本書の一部をオンラインで公開しています。\nhttps://koki0702.github.io/dezero-book/\n\n\n## ファイル構成\n\n|フォルダ名 |説明         |\n|:--        |:--                  |\n|[dezero](/dezero)       |DeZeroのソースコード|\n|[examples](/examples)     |DeZeroを使った実装例|\n|[steps](/steps)|各stepファイル（step01.py ~ step60.py）|\n|[tests](/tests)|DeZeroのユニットテスト|\n\n\n## 必要な外部ライブラリ\n\n本書で使用するPytnonのバージョンと外部ライブラリは下記の通りです。\n\n- [Python 3系](https://docs.python.org/3/)\n- [NumPy](https://numpy.org/)\n- [Matplotlib](https://matplotlib.org/)\n\nまたオプションとして、NVIDIAのGPUで実行できる機能も提供します。その場合は下記のライブラリが必要です。\n\n- [CuPy](https://cupy.chainer.org/) （オプション）\n\n\n## 実行方法\n\n本書で説明するPythonファイルは、主に[steps](/steps)ファルダにあります。\n実行するためには、下記のとおりPythonコマンドを実行します（どのディレクトリからでも実行できます）。\n\n```\n$ python steps/step01.py\n$ python steps/step02.py\n\n$ cd steps\n$ python step31.py\n```\n\n## デモ\n\nDeZeroの他の実装例は[examples](/examples)にあります。\n\n[\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/example_tanh.png\" height=\"175\"/\u003e](https://github.com/oreilly-japan/deep-learning-from-scratch-3/tree/tanh)[\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/example_spiral.png\" height=\"175\"/\u003e](/examples/spiral.py)[\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/example_gpu.png\" height=\"175\"/\u003e](https://colab.research.google.com/github/oreilly-japan/deep-learning-from-scratch-3/blob/master/examples/mnist_colab_gpu.ipynb)\n\n[\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/gan.gif\" height=\"175\"/\u003e](/examples/gan.py)[\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/vae.png\" height=\"175\"/\u003e](/examples/vae.py)[\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/grad_cam.png\" height=\"175\"/\u003e](/examples/grad_cam.py)\n\n[\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/style_transfer.png\" height=\"175\"/\u003e](/examples/style_transfer.py)[\u003cimg src=\"https://raw.githubusercontent.com/oreilly-japan/deep-learning-from-scratch-3/images/pythonista.png\" height=\"175\"/\u003e](https://github.com/oreilly-japan/deep-learning-from-scratch-3/wiki/DeZero%E3%82%92iPhone%E3%81%A7%E5%8B%95%E3%81%8B%E3%81%99)\n\n## 正誤表\n\n本書の正誤情報は、[:mag_right: 正誤表ページ](../../wiki/Errata)に掲載しています。\n\n正誤表ページに掲載されていない誤植や間違いなどを見つけた方は、[:email: japan@oreilly.co.jp](\u003cmailto:japan@oreilly.co.jp\u003e)までお知らせください。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foreilly-japan%2Fdeep-learning-from-scratch-3","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Foreilly-japan%2Fdeep-learning-from-scratch-3","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Foreilly-japan%2Fdeep-learning-from-scratch-3/lists"}