{"id":28498848,"url":"https://github.com/gitycc/tensorflow_tutorial","last_synced_at":"2025-07-03T22:31:23.746Z","repository":{"id":26491610,"uuid":"109019873","full_name":"GitYCC/Tensorflow_Tutorial","owner":"GitYCC","description":"Step by step, Let you learn how to use tensorflow in practical.","archived":false,"fork":false,"pushed_at":"2022-11-22T02:39:24.000Z","size":13425,"stargazers_count":30,"open_issues_count":4,"forks_count":26,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-06-08T14:06:43.308Z","etag":null,"topics":["deep-learning","machine-learning","neurel-network","tensorflow"],"latest_commit_sha":null,"homepage":"https://www.ycc.idv.tw/tag/tensorflow.html","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/GitYCC.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}},"created_at":"2017-10-31T16:03:45.000Z","updated_at":"2022-07-05T10:02:38.000Z","dependencies_parsed_at":"2023-01-14T08:30:29.680Z","dependency_job_id":null,"html_url":"https://github.com/GitYCC/Tensorflow_Tutorial","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GitYCC/Tensorflow_Tutorial","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitYCC%2FTensorflow_Tutorial","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitYCC%2FTensorflow_Tutorial/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitYCC%2FTensorflow_Tutorial/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitYCC%2FTensorflow_Tutorial/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GitYCC","download_url":"https://codeload.github.com/GitYCC/Tensorflow_Tutorial/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GitYCC%2FTensorflow_Tutorial/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263415047,"owners_count":23463080,"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","machine-learning","neurel-network","tensorflow"],"created_at":"2025-06-08T14:06:38.243Z","updated_at":"2025-07-03T22:31:23.713Z","avatar_url":"https://github.com/GitYCC.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 實作Tensorflow系列教程\n\n## 一步一腳印的學Tensorflow\n\n我想完成一套Tensorflow教程，將Deep Learning一些重要的概念一一的點出來，並且使用Tensorflow來實現或驗證這些概念。本教程有三個面向我希望做到的，我希望觀念講解時可以深入淺出，我希望呈現程式碼時可以結構嚴謹，我希望可以完整呈現Tensorflow的實用面。\n\n**本教程「網頁版」請至我的個人網站查看：[http://www.ycc.idv.tw/tag__實作Tensorflow/](http://www.ycc.idv.tw/tag__實作Tensorflow/)**\n\n## Ch01 Simple Logistic Classification on MNIST\n\n建立一個簡單的單層Neurel Network。\n\n![Simple Neurel Network](https://raw.githubusercontent.com/GitYCC/Tensorflow_Tutorial/master/img/TensorflowTutorial.002.jpeg)\n\n## Ch02 Build First Deep Neurel Network (DNN)\n\n開始建立第一個Deep Learning，並仔細介紹Deep Learning的重要組成，包括：Hidden Layer、Activation Function、Mini-Batch Gradient Descent、Weight Regularization、Dropout和Optimizer。\n\n![DNN](https://raw.githubusercontent.com/GitYCC/Tensorflow_Tutorial/master/img/TensorflowTutorial.003.jpeg)\n\n## Ch03 Build First Convolutional Neurel Network (CNN)\n\n介紹影像處理上最廣為人使用的Convolutional Neurel Network，引入Convolution Layer和Pooling Layer的概念，並在最後完成最簡單的CNN架構：LeNet5。\n\n![CNN](https://raw.githubusercontent.com/GitYCC/Tensorflow_Tutorial/master/img/TensorflowTutorial.006.jpeg)\n\n## Ch04 Autoencoder\n\n建立一個DNN的Autoencoder，揭露Embedding Code的神奇效果，藉由壓縮與還原找出一個精簡描述一群數據的Embedding空間，在這空間上數據不需要人為給予Labels，機器會自行分類成為一個個合理的群體，所以Autoencoder可以用於Unsupervised Learning上。\n\n![Autoencoder](https://github.com/GitYCC/Tensorflow_Tutorial/blob/master/img/TensorflowTutorial.007.jpeg?raw=true)\n\n![Embedding Code](https://raw.githubusercontent.com/GitYCC/Tensorflow_Tutorial/master/img/04_output_9_0.png)\n\n## Ch05 Word2Vec\n\n介紹兩種Word2Vec模型：Skip-gram和CBOW，揭露Embedding Vector的神奇效果，利用壓縮上下文的關係，我們可以建立一個Embedding的空間，在這個空間語意相近的兩個字，它們的Embedding Vector也會彼此相似。\n\n![word2vec](https://raw.githubusercontent.com/GitYCC/Tensorflow_Tutorial/master/img/TensorflowTutorial.008.jpeg)\n\n![Embedding Vector](https://raw.githubusercontent.com/GitYCC/Tensorflow_Tutorial/master/img/05_output_13_0.png)\n\n## CH06 Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM)\n\n介紹具有時序性的Neurel Network—RNN，並點出一般簡易型的RNN因為共用權重以及等效於非常深的網路，會遇到的梯度爆炸與梯度消失問題。LSTM是另外一種型態的RNN，利用建立「長期記憶」來避免梯度消失問題，至於梯度爆炸問題則可以使用Gradient Clipping的手法解決。\n\n![LSTM](https://github.com/GitYCC/Tensorflow_Tutorial/raw/master/img/TensorflowTutorial.012.jpeg)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgitycc%2Ftensorflow_tutorial","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgitycc%2Ftensorflow_tutorial","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgitycc%2Ftensorflow_tutorial/lists"}