Deep-Learning-Tensorflow

Purely Tensorflow, no Keras or other abstract libraries of Tensorflow

Dependencies

sudo pip install scipy numpy matplotlib librosa pandas seaborn

• I recommended install Tensorflow from source, way more faster
• If you got GPU, compile it with CUDA
• You need to download CIFAR-10, CIFAR-100

Basic-Seq2Seq

Generate encoder and decoder by creating 2 Deep Recurrent Neural Network to predict incoming text link notebook

Chatbot-Attention-Seq2Seq

Generate chatbot using attention model on Sequence-to-Sequence Tensorflow API link notebook

DCGAN (Simplify and Original for House Number)

link notebook

WGAN Improvement

link notebook

DiscoGAN (original paper and Fashion MNIST)

link notebook

Residual Network for CIFAR-10

link notebook

Deep Convolutional

1. trained to label 100 classes link folder

2. trained to label multitags, a single picture can be more than 1 tag link notebook

3. trained to predict pokemon type link notebook

Deep Recurrent

1. trained to predict stock market link notebook

2. trained to generate sentence link notebook

3. trained to classify sentiment link notebook

Essay-Attention-Seq2Seq

link notebook

Multi-Perceptron

1. Creditcard detection (softmax, l2 loss, 4 hidden layers) link notebook

2. detect-voice (softmax, dropout, l2 loss, 4 hidden layers) link notebook

3. iris (3 hidden layers, softmax) link notebook

4. pokemon (4 hidden layers, softmax) link notebook

5. sentiment (6 hidden layers, batch normalization, l2 loss, dropout) link notebook

Introduction on layer normalization

link notebook

Encoder model, both multi-perceptron and Convolutional

1. multi-perceptron link notebook

2. Convolutional link notebook

Word vector both using softmax and NCE

1. softmax link notebook

2. NCE link notebook