Collection of (Little More + Refactored) Advanced TensorFlow Implementations. Try my best to implement algorithms with a single Jupyter Notebook.

• Denoising AutoEncoder
• Convolutional AutoEncoder (using deconvolution)
• Variational AutoEncoder

• AVB on 2-dimensional Toy Example

• Basic Classification (MLP and CNN)
• Custom Dataset Generation
• Classification (MLP and CNN) using Custom Dataset
• OOP Style Implementation of MLP and CNN

• Pretrained Network Usage with TF-SLIM
• Class Activation Map with Pretrained Network

• Preprocess Linux Kernel Sources
• Train and Sample with Char-RNN

• Domain Adversarial Neural Network with Gradient Reversal Layer

• Deep Convolutional Generative Adversarial Network with MNIST

• Mixture Density Network
• Heteroscedastic Mixture Density Network

• Model Based RL (Value Iteration and Policy Iteration)

• MNIST Classification with TF-SLIM

• Super-resolution with Generative Adversarial Network

• Python-2.7
• TensorFlow-1.0.1
• SciPy
• MatplotLib
• Jupyter Notebook