• 关于生活事项

I chose a very simple project to be implemented to finish the whole classs inasmuch as in CS231n course, students were left a project to be done themselves. Well, this could be very simple and basic because I haven’t learnt very detail and implemented all assignments by myself. And this tiny project will be my every first tensorflow & Computer vision project, later on I hope that I can make something creative like advanced style transfer. : )

Life is short, I use python

The following contents and images are from cs224n and hankcs.

Yesterday I finished a vanilla recurrent neural networks and used them to train a model that could generate novel captions for images. It’s really excited that as the the domain of NLP, word embedding can be combining with Computer Vision CNN for image captioning,which is sort of like Lego construction.(All the images drawn in draft are from link )

Right now Pytorch and Tensorflow are the extremely popular AI frameworks , but AI researchers may find it a little bit tangled when it comes to the question that which framework to use. So rather than choose one of them to learn, why not use both of them since they will come in handy later on. So I’m going to introduce both of them from the perspective of  vanilla structure and API.