Pix2Pix image translation using conditional adversarial network - sketch to face
I have decided to repost my github repository here since I would like to get some feedbacks and ideas using the Disque below. After reading Phillip Isola’s Paper and Torch implement, and Christopher Hesse’s pix2pix tensorflow implementation and blog. I am very impressive with the power of conditional adversarial network and samples outcomes. And I decided to give it a try on some data set on the wild. After failing on a number of ideas, I came across the CUHK Face Sketch database. I realized the network will be perfect for this kind of project.
Text Classification, Part 3 - Hierarchical attention network
After the exercise of building convolutional, RNN, sentence level attention RNN, finally I have come to implement Hierarchical Attention Networks for Document Classification. I’m very thankful to Keras, which make building this project painless. The custom layer is very powerful and flexible to build your custom logic to embed into the existing frame work. Functional API makes the Hierarchical InputLayers very easy to implement.
Text Classification, Part 2 - sentence level Attentional RNN
In the second post, I will try to tackle the problem by using recurrent neural network and attention based LSTM encoder. Further, to make one step closer to implement Hierarchical Attention Networks for Document Classification, I will implement an Attention Network on top of LSTM/GRU for the classification task.
Text Classification, Part I - Convolutional Networks
Text classification is a very classical problem. The goal is to classify documents into a fixed number of predefined categories, given a variable length of text bodies. It is widely use in sentimental analysis (IMDB, YELP reviews classification), stock market sentimental analysis, to GOOGLE’s smart email reply. This is a very active research area both in academia and industry. In the following series of posts, I will try to present a few different approaches and compare their performances. Ultimately, the goal for me is to implement the paper Hierarchical Attention Networks for Document Classification.