---

tensorflow-basic-and-advanced

tensorflow for deep learning

Requirements

• tensorFlow
• numpy
• scipy
• scikit-learn
• matplotlib

Basic

• lab01 Basic regression

  • [lab01-1] linear regression
  • [lab01-2] linear regression get_variable
  • [lab01-3] linear regression using function
  • [lab01-4] linear regression compute gradient
  • [lab01-5] ridge regression
  • [lab01-6] lasso regression
  • [lab01-7] support vector regression
  • [lab01-8] deep regression

• lab02 Basic classification

  • [lab02-1] classifier logistic regression
  • [lab02-2] classifier softmax regression
  • [lab02-3] classifier support vector regression
  • [lab02-4] classifier multi class softmax regression
  • [lab02-5] classifier multi class svm

• lab03 Usage of tensorboard

  • [lab03-1] tensorboard basic usages
  • [lab03-2] tensorboard var scope
  • [lab03-3] tensorboard summary
  • [lab03-4] tensorboard device
  • [lab03-5] tensorboard many models

• lab04 Data manipulation

  • [lab04-1] data manipulation load csv
  • [lab04-2] data manipulation npy
  • [lab04-3] data manipulation train test validation
  • [lab04-4] data manipulation minibatch
  • [lab04-5] data manipulation tfrecord write1
  • [lab04-6] data manipulation tfrecord read1
  • [lab04-7] data manipulation tfrecord write2
  • [lab04-8] data manipulation tfrecord read2
  • [lab04-9] data manipulation queue

• lab05 Activation functions

  • [lab05-1] activation sigmoid
  • [lab05-2] activation tanh
  • [lab05-3] activation relu
  • [lab05-4] activation leaky relu
  • [lab05-5] activation relu with xavier

• lab06 Optimizers

  • [lab06-1] optimizer gradient descent
  • [lab06-2] optimizer momentum
  • [lab06-3] optimizer adadelta
  • [lab06-4] optimizer adagrad
  • [lab06-5] optimizer rmsporp
  • [lab06-6] optimizer adam

• lab07 Regularization

  • [lab07-1] l1 regularization
  • [lab07-2] l2 regularization
  • [lab07-3] dropout
  • [lab07-4] batch normalization
  • [lab07-5] batch normalization and dropout

• lab08 CNN

  • [lab08-0] mnist and cifar
  • [lab08-1] cnn mnist base
  • [lab08-2] cnn mnist learning rate decay
  • [lab08-3] cnn mnist dropout
  • [lab08-4] cnn mnist batch normalization
  • [lab08-5] cnn mnist batch normalization and dropout
  • [lab08-6] cnn mnist svm loss
  • [lab08-7] cnn cifar base
  • [lab08-8] cnn cifar batch normalization and dropout1
  • [lab08-9] cnn cifar batch normalization and dropout2
  • [lab08-X] cnn cifar batch normalization and dropout3

• lab09 RNN

  • [lab09-1] rnn sequence labeling base
  • [lab09-2] rnn sequence labeling LSTM
  • [lab09-3] rnn sequence labeling peephole
  • [lab09-4] rnn sequence labeling gradient clipping
  • [lab09-5] rnn sequence labeling gradient normalization
  • [lab09-6] rnn sequence labeling dropout
  • [lab09-7] rnn sequence labeling stacked LSTM
  • [lab09-8] rnn sequence labeling deep LSTM

• lab10 Some techniques

  • [lab10-1] model save
  • [lab10-2] model restore
  • [lab10-3] model flags
  • [lab10-4] model class
  • [lab10-5] model decorator

References

blog

• Danijar Hafner, https://danijar.com

github

• Hwalsuk Lee, https://github.com/hwalsuklee
• Sunghun Kim, https://github.com/hunkim/DeepLearningZeroToAll

site

• Go Deep, http://www.godeep.ml/

book

No	Name	Author	Years
1	TensorFlow for Machine Intelligence: A Hands-On Introduction to Learning Algorithms	Sam Abrahams, Danijar Hafner, Erik Erwitt, Ariel Scarpinelli	2016
2	First Contact With Tensorflow	Jordi Torres	2016
3	Learning TensorFlow: A Guide to Building Deep Learning Systems	Tom Hope, Yehezkel S. Resheff, Itay Lieder	2017
4	Tensorflow Machine Learning Cookbook	Nick McClure	2017