Machines today can identify objects in images, but they are unable to fully decipher the most important aspect: what’s actually happening in front of the camera. At TwentyBN, we have created the world’s first AI technology that shows an awareness of its environment and of the actions occurring within it. Our system observes the world through live video and automatically interprets the unfolding visual scene. Check it out yourself:
When I first started study PyTorch, I drop it after a few days. It was hard for me to get core concepts of this framework comparing with the TensorFlow. That’s why I’ve put it on my “knowledge bookshelf” and forgot about it. But not so far ago a new version of PyTorch was released. So I’ve decided to give it a chance again. After a while, I understood that this framework is really easy to use and it makes me happy to code in PyTorch. In this post, I will try to explain core concepts of it clearly so that you will be motivated at least give it a try right now, not after a few years or more. We will cover some basic principles and some advanced stuff as learning rate schedulers, custom layers and more.
I’m taking a break from my discussion on asyncio in Python to talk about something that has been on my mind recently: the speed of Python. For those who don’t know, I am somewhat of a Python fanboy, and I aggressively use Python everywhere I can. One of the biggest complaints people have against Python is that it’s slow. Some people almost refuse to even try python because its slower than X. Here are my thoughts as to why you should try python, despite it being slow.