A while ago I started building a website using Django as its backend and Vue.js as its frontend. Unlike other apps, however, there is a twist: it is multi-page. The website should resemble a normal website built natively on Django, with multiple urls and the ability to jump into any page (without faking it with vue-router) as well as Vue’s reactiveness. So, after digging around various tutorials and guides, none of which fully answered the question, I would like to share my piece in solving the equation.
Introduction and TLDR
This post will start with the basics of using Vue.js and Django. Then, it will move on to use more advanced tools such as webpack to serve the Vue.js frontend on Django. Finally, we will be modifying it a bit to serve multi-page Vue.js.
I have also created a Github repo that includes the finished project of this tutorial. You can check it out at (gundamMC/vue-django-multipage-example).Continue reading →
Over the past few months, I’ve been working on a RNN chatbot. However, I soon ran into a weird issue. In short, the network repeatedly outputted the same tokens (often <EOS> or <GO>). The longer version is on Stack Overflow.
After months of digging around, I’ve finally found the issue. When training a RNN (with TrainingHelper and BasicDecoder), Tensorflow expects the ground-truth inputs with <GO> tokens but then outputs without <GO>. Basically,
Encoder input: <GO> foo foo foo <EOS>
Decoder input/ground truth: <GO> bar bar bar <EOS>
Decoder output: bar bar bar <EOS> <EOS/PAD>
Since I used <GO> in both the inputs and outputs, the model repeated itself. (<GO> -> <GO>, bar -> bar).
After fixing this and a few other small issues, the chatbot started to produce acceptable results. I will be posting an update on the chatbot soon, as this is only a reminder to myself and a tip for the ones having the same issue.
Over the last few weeks I’ve been working on a deep neural net to predict website credibility (i.e. how “reliable” it is). The features consist of basic website features such as its domain and a bag-of-words model.
Website credibility is determined by a lot of things and a lot of the time there isn’t a right or wrong answer. Wikipedia, for example, is a notorious source because it can be edited by anyone. Nonetheless, Wikipedia does contain a lot of correct and is still considered unreliable.
Although there is no exact answer, we can often predict the credibility through many features such as the author, the “purpose” of the text, and even the date. (More can be found here)
Continue reading →