導語:本文是TensorFlow實現(xiàn)流行機器學習算法的教程匯集,目標是讓讀者可以輕松通過清晰簡明的案例深入了解 TensorFlow羞福。這些案例適合那些想要實現(xiàn)一些 TensorFlow 案例的初學者畦徘。本教程包含還包含筆記和帶有注解的代碼剃幌。第一步:給TF新手的教程指南
1:tf初學者需要明白的入門準備
機器學習入門筆記:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/0_Prerequisite/ml_introduction.ipynb
MNIST 數(shù)據(jù)集入門筆記
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/0_Prerequisite/mnist_dataset_intro.ipynb
2:tf初學者需要了解的入門基礎
Hello World
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1_Introduction/helloworld.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/helloworld.py
基本操作
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1_Introduction/basic_operations.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/basic_operations.py
3:tf初學者需要掌握的基本模型
最近鄰:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/nearest_neighbor.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/nearest_neighbor.py
線性回歸:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/linear_regression.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/linear_regression.py
Logistic 回歸:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/logistic_regression.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/logistic_regression.py
4:tf初學者需要嘗試的神經(jīng)網(wǎng)絡
多層感知器:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/multilayer_perceptron.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/multilayer_perceptron.py
卷積神經(jīng)網(wǎng)絡:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/convolutional_network.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/convolutional_network.py
循環(huán)神經(jīng)網(wǎng)絡(LSTM):
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/recurrent_network.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py
雙向循環(huán)神經(jīng)網(wǎng)絡(LSTM):
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/bidirectional_rnn.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/bidirectional_rnn.py
動態(tài)循環(huán)神經(jīng)網(wǎng)絡(LSTM)
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/dynamic_rnn.py
自編碼器
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/autoencoder.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/autoencoder.py
5:tf初學者需要精通的實用技術
保存和恢復模型
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4_Utils/save_restore_model.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/save_restore_model.py
圖和損失可視化
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4_Utils/tensorboard_basic.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/tensorboard_basic.py
Tensorboard——高級可視化
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/tensorboard_advanced.py
5:tf初學者需要的懂得的多GPU基本操作
多 GPU 上的基本操作
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/5_MultiGPU/multigpu_basics.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/5_MultiGPU/multigpu_basics.py
6:案例需要的數(shù)據(jù)集
有一些案例需要 MNIST 數(shù)據(jù)集進行訓練和測試恰响。運行這些案例時劫笙,該數(shù)據(jù)集會被自動下載下來(使用 input_data.py)芙扎。
MNIST數(shù)據(jù)集筆記:https://github.com/aymericdamien ... dataset_intro.ipynb
官方網(wǎng)站:http://yann.lecun.com/exdb/mnist/
第二步:為TF新手準備的各個類型的案例、模型和數(shù)據(jù)集
初步了解:TFLearn?TensorFlow
接下來的示例來自TFLearn填大,這是一個為 TensorFlow 提供了簡化的接口的庫戒洼。里面有很多示例和預構建的運算和層。
使用教程:TFLearn 快速入門允华。通過一個具體的機器學習任務學習 TFLearn 基礎圈浇。開發(fā)和訓練一個深度神經(jīng)網(wǎng)絡分類器。
TFLearn地址:https://github.com/tflearn/tflearn
示例:https://github.com/tflearn/tflearn/tree/master/examples
預構建的運算和層:http://tflearn.org/doc_index/#api
筆記:https://github.com/tflearn/tflea ... intro/quickstart.md
基礎模型以及數(shù)據(jù)集
線性回歸例获,使用 TFLearn 實現(xiàn)線性回歸
https://github.com/tflearn/tflearn/blob/master/examples/basics/linear_regression.py
邏輯運算符汉额。使用 TFLearn 實現(xiàn)邏輯運算符
https://github.com/tflearn/tflearn/blob/master/examples/basics/logical.py
權重保持曹仗。保存和還原一個模型
https://github.com/tflearn/tflearn/blob/master/examples/basics/weights_persistence.py
微調榨汤。在一個新任務上微調一個預訓練的模型
https://github.com/tflearn/tflearn/blob/master/examples/basics/finetuning.py
使用 HDF5。使用 HDF5 處理大型數(shù)據(jù)集
https://github.com/tflearn/tflearn/blob/master/examples/basics/use_hdf5.py
使用 DASK怎茫。使用 DASK 處理大型數(shù)據(jù)集
https://github.com/tflearn/tflearn/blob/master/examples/basics/use_dask.py
計算機視覺模型及數(shù)據(jù)集
多層感知器收壕。一種用于 MNIST 分類任務的多層感知實現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/dnn.py
卷積網(wǎng)絡(MNIST)。用于分類 MNIST 數(shù)據(jù)集的一種卷積神經(jīng)網(wǎng)絡實現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_mnist.py
卷積網(wǎng)絡(CIFAR-10)轨蛤。用于分類 CIFAR-10 數(shù)據(jù)集的一種卷積神經(jīng)網(wǎng)絡實現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_cifar10.py
網(wǎng)絡中的網(wǎng)絡蜜宪。用于分類 CIFAR-10 數(shù)據(jù)集的 Network in Network 實現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/network_in_network.py
Alexnet。將 Alexnet 應用于 Oxford Flowers 17 分類任務
https://github.com/tflearn/tflearn/blob/master/examples/images/alexnet.py
VGGNet祥山。將 VGGNet 應用于 Oxford Flowers 17 分類任務
https://github.com/tflearn/tflearn/blob/master/examples/images/vgg_network.py
VGGNet Finetuning (Fast Training)圃验。使用一個預訓練的 VGG 網(wǎng)絡并將其約束到你自己的數(shù)據(jù)上,以便實現(xiàn)快速訓練
https://github.com/tflearn/tflearn/blob/master/examples/images/vgg_network_finetuning.py
RNN Pixels缝呕。使用 RNN(在像素的序列上)分類圖像
https://github.com/tflearn/tflearn/blob/master/examples/images/rnn_pixels.py
Highway Network澳窑。用于分類 MNIST 數(shù)據(jù)集的 Highway Network 實現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/highway_dnn.py
Highway Convolutional Network。用于分類 MNIST 數(shù)據(jù)集的 Highway Convolutional Network 實現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_highway_mnist.py
Residual Network (MNIST) 供常。應用于 MNIST 分類任務的一種瓶頸殘差網(wǎng)絡(bottleneck residual network)
https://github.com/tflearn/tflearn/blob/master/examples/images/residual_network_mnist.py
Residual Network (CIFAR-10)摊聋。應用于 CIFAR-10 分類任務的一種殘差網(wǎng)絡
https://github.com/tflearn/tflearn/blob/master/examples/images/residual_network_cifar10.py
Google Inception(v3)。應用于 Oxford Flowers 17 分類任務的谷歌 Inception v3 網(wǎng)絡
https://github.com/tflearn/tflearn/blob/master/examples/images/googlenet.py
自編碼器栈暇。用于 MNIST 手寫數(shù)字的自編碼器
https://github.com/tflearn/tflearn/blob/master/examples/images/autoencoder.py
自然語言處理模型及數(shù)據(jù)集
循環(huán)神經(jīng)網(wǎng)絡(LSTM)麻裁,應用 LSTM 到 IMDB 情感數(shù)據(jù)集分類任
https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm.py
雙向 RNN(LSTM),將一個雙向 LSTM 應用到 IMDB 情感數(shù)據(jù)集分類任務:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/bidirectional_lstm.py
動態(tài) RNN(LSTM),利用動態(tài) LSTM 從 IMDB 數(shù)據(jù)集分類可變長度文本:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/dynamic_lstm.py
城市名稱生成煎源,使用 LSTM 網(wǎng)絡生成新的美國城市名:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm_generator_cityname.py
莎士比亞手稿生成色迂,使用 LSTM 網(wǎng)絡生成新的莎士比亞手稿:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm_generator_shakespeare.py
Seq2seq,seq2seq 循環(huán)網(wǎng)絡的教學示例:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/seq2seq_example.py
CNN Seq薪夕,應用一個 1-D 卷積網(wǎng)絡從 IMDB 情感數(shù)據(jù)集中分類詞序列
https://github.com/tflearn/tflearn/blob/master/examples/nlp/cnn_sentence_classification.py
強化學習案例
Atari Pacman 1-step Q-Learning脚草,使用 1-step Q-learning 教一臺機器玩 Atari 游戲:
https://github.com/tflearn/tflearn/blob/master/examples/reinforcement_learning/atari_1step_qlearning.py
第三步:為TF新手準備的其他方面內容
Recommender-Wide&Deep Network,推薦系統(tǒng)中 wide & deep 網(wǎng)絡的教學示例:
https://github.com/tflearn/tflearn/blob/master/examples/others/recommender_wide_and_deep.py
Spiral Classification Problem原献,對斯坦福 CS231n spiral 分類難題的 TFLearn 實現(xiàn):
https://github.com/tflearn/tflearn/blob/master/examples/notebooks/spiral.ipynb
層馏慨,與 TensorFlow 一起使用??TFLearn 層:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/layers.py
訓練器,使用 TFLearn 訓練器類訓練任何 TensorFlow 圖:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/layers.py
Bulit-in Ops姑隅,連同 TensorFlow 使用 TFLearn built-in 操作:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/builtin_ops.py
Summaries写隶,連同 TensorFlow 使用 TFLearn summarizers:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/summaries.py
Variables,連同 TensorFlow 使用 TFLearn Variables:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/variables.py