文章來源:Github
本文是TensorFlow實(shí)現(xiàn)流行機(jī)器學(xué)習(xí)算法的教程匯集锤躁,目標(biāo)是讓讀者可以輕松通過清晰簡明的案例深入了解 TensorFlow。這些案例適合那些想要實(shí)現(xiàn)一些TensorFlow案例的初學(xué)者鞋屈。本教程包含還包含筆記和帶有注解的代碼戴卜。
第一步:給TF新手的教程指南
1:tf初學(xué)者需要明白的入門準(zhǔn)備
機(jī)器學(xué)習(xí)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(xué)者需要了解的入門基礎(chǔ)
Hello World
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1_Introduction/helloworld.ipynb
基本操作代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/helloworld.py
基本操作
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1_Introduction/basic_operations.ipynb
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/basic_operations.py
3:tf初學(xué)者需要掌握的基本模型
最近鄰:
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/nearest_neighbor.ipynb
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/nearest_neighbor.py
線性回歸:
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/linear_regression.ipynb
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/linear_regression.py
Logistic 回歸:
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/logistic_regression.ipynb
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/logistic_regression.py
4:tf初學(xué)者需要嘗試的神經(jīng)網(wǎng)絡(luò)
多層感知器:
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/multilayer_perceptron.ipynb
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/multilayer_perceptron.py
卷積神經(jīng)網(wǎng)絡(luò):
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/convolutional_network.ipynb
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/convolutional_network.py
循環(huán)神經(jīng)網(wǎng)絡(luò)(LSTM):
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/recurrent_network.ipynb
代碼: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(luò)(LSTM):
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/bidirectional_rnn.ipynb
代碼: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(luò)(LSTM)
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/dynamic_rnn.py
自編碼器
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/autoencoder.ipynb
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/autoencoder.py
5:tf初學(xué)者需要精通的實(shí)用技術(shù)
保存和恢復(fù)模型
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4_Utils/save_restore_model.ipynb
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/save_restore_model.py
圖和損失可視化
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4_Utils/tensorboard_basic.ipynb
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/tensorboard_basic.py
Tensorboard——高級可視化
代碼:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/tensorboard_advanced.py
5:tf初學(xué)者需要的懂得的多GPU基本操作
多 GPU 上的基本操作
筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/5_MultiGPU/multigpu_basics.ipynb
代碼: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(jìn)行訓(xùn)練和測試捣域。運(yùn)行這些案例時啼染,該數(shù)據(jù)集會被自動下載下來(使用 input_data.py)。
MNIST數(shù)據(jù)集筆記:https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/0_Prerequisite/mnist_dataset_intro.ipynb
官方網(wǎng)站:http://yann.lecun.com/exdb/mnist/
第二步:為TF新手準(zhǔn)備的各個類型的案例焕梅、模型和數(shù)據(jù)集
初步了解:TFLearnTensorFlow
接下來的示例來自TFLearn迹鹅,這是一個為 TensorFlow 提供了簡化的接口的庫。里面有很多示例和預(yù)構(gòu)建的運(yùn)算和層贞言。
使用教程:TFLearn 快速入門斜棚。通過一個具體的機(jī)器學(xué)習(xí)任務(wù)學(xué)習(xí) TFLearn 基礎(chǔ)。開發(fā)和訓(xùn)練一個深度神經(jīng)網(wǎng)絡(luò)分類器该窗。
TFLearn地址:https://github.com/tflearn/tflearn
示例:https://github.com/tflearn/tflearn/tree/master/examples
預(yù)構(gòu)建的運(yùn)算和層:http://tflearn.org/doc_index/#api
筆記:https://github.com/tflearn/tflearn/blob/master/tutorials/intro/quickstart.md
基礎(chǔ)模型以及數(shù)據(jù)集
線性回歸弟蚀,使用 TFLearn 實(shí)現(xiàn)線性回歸
https://github.com/tflearn/tflearn/blob/master/examples/basics/linear_regression.py
邏輯運(yùn)算符。使用 TFLearn 實(shí)現(xiàn)邏輯運(yùn)算符
https://github.com/tflearn/tflearn/blob/master/examples/basics/logical.py
權(quán)重保持酗失。保存和還原一個模型
https://github.com/tflearn/tflearn/blob/master/examples/basics/weights_persistence.py
微調(diào)义钉。在一個新任務(wù)上微調(diào)一個預(yù)訓(xùn)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规肴。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(jì)算機(jī)視覺模型及數(shù)據(jù)集
多層感知器捶闸。一種用于 MNIST 分類任務(wù)的多層感知實(shí)現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/dnn.py
卷積網(wǎng)絡(luò)(MNIST)。用于分類 MNIST 數(shù)據(jù)集的一種卷積神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_mnist.py
卷積網(wǎng)絡(luò)(CIFAR-10)奏纪。用于分類 CIFAR-10 數(shù)據(jù)集的一種卷積神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_cifar10.py
網(wǎng)絡(luò)中的網(wǎng)絡(luò)鉴嗤。用于分類 CIFAR-10 數(shù)據(jù)集的 Network in Network 實(shí)現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/network_in_network.py
Alexnet。將 Alexnet 應(yīng)用于 Oxford Flowers 17 分類任務(wù)
https://github.com/tflearn/tflearn/blob/master/examples/images/alexnet.py
VGGNet序调。將 VGGNet 應(yīng)用于 Oxford Flowers 17 分類任務(wù)
https://github.com/tflearn/tflearn/blob/master/examples/images/vgg_network.py
VGGNet Finetuning (Fast Training)。使用一個預(yù)訓(xùn)練的 VGG 網(wǎng)絡(luò)并將其約束到你自己的數(shù)據(jù)上兔簇,以便實(shí)現(xiàn)快速訓(xùn)練
https://github.com/tflearn/tflearn/blob/master/examples/images/vgg_network_finetuning.py
RNN Pixels发绢。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硬耍。用于分類 MNIST 數(shù)據(jù)集的 Highway Network 實(shí)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(shí)現(xiàn)
https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_highway_mnist.py
Residual Network (MNIST) 边酒。應(yīng)用于 MNIST 分類任務(wù)的一種瓶頸殘差網(wǎng)絡(luò)(bottleneck residual network)
https://github.com/tflearn/tflearn/blob/master/examples/images/residual_network_mnist.py
Residual Network (CIFAR-10)经柴。應(yīng)用于 CIFAR-10 分類任務(wù)的一種殘差網(wǎng)絡(luò)
https://github.com/tflearn/tflearn/blob/master/examples/images/residual_network_cifar10.py
Google Inception(v3)。應(yīng)用于 Oxford Flowers 17 分類任務(wù)的谷歌 Inception v3 網(wǎng)絡(luò)
https://github.com/tflearn/tflearn/blob/master/examples/images/googlenet.py
自編碼器墩朦。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(luò)(LSTM)坯认,應(yīng)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(yīng)用到 IMDB 情感數(shù)據(jù)集分類任務(wù):
https://github.com/tflearn/tflearn/blob/master/examples/nlp/bidirectional_lstm.py
動態(tài) RNN(LSTM)氓涣,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
城市名稱生成牛哺,使用 LSTM 網(wǎng)絡(luò)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,使用 LSTM 網(wǎng)絡(luò)生成新的莎士比亞手稿:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm_generator_shakespeare.py
Seq2seq劳吠,seq2seq 循環(huán)網(wǎng)絡(luò)的教學(xué)示例:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/seq2seq_example.py
CNN Seq引润,應(yīng)用一個 1-D 卷積網(wǎng)絡(luò)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(qiáng)化學(xué)習(xí)案例
Atari Pacman 1-step Q-Learning,使用 1-step Q-learning 教一臺機(jī)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(zhǔn)備的其他方面內(nèi)容
Recommender-Wide&Deep Network痒玩,推薦系統(tǒng)中 wide & deep 網(wǎng)絡(luò)的教學(xué)示例:
https://github.com/tflearn/tflearn/blob/master/examples/others/recommender_wide_and_deep.py
Spiral Classification Problem淳附,對斯坦福 CS231n spiral 分類難題的 TFLearn 實(shí)現(xiàn):
https://github.com/tflearn/tflearn/blob/master/examples/notebooks/spiral.ipynb
層,與 TensorFlow 一起使用 ?TFLearn 層:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/layers.py
訓(xùn)練器蠢古,使用 TFLearn 訓(xùn)練器類訓(xùn)練任何 TensorFlow 圖:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/layers.py
Bulit-in Ops奴曙,連同 TensorFlow 使用 TFLearn built-in 操作:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/builtin_ops.py
Summaries,連同 TensorFlow 使用 TFLearn summarizers:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/summaries.py
Variables草讶,連同 TensorFlow 使用 TFLearn Variables:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/variables.py