It is a well-known fact that deep learning models are heavy; with a lot of weights for the deep layers. And it is obviously an overhead to load the model every time we need to get the predictions from the model. Thus this is costly in terms of the time of execution.
In this project, we will mainly focus on addressing this issue, by uniquely integrating the networking functionalities provided by ZMQ library. We will build a server-client based architecture to make the model load exactly once(that is during the starting of the app). The predictions from the model will be served by the model server, as long as it listens to its Flask client which requests it for the predictions for an input image.
REVA University signs an MoU with CloudxLab to set up a Center of Excellence in AI and Deep Technologies: In the picture, Dr. K.M Babu, Vice Chancellor, Dr. Dhanamjaya, Pro-Vice Chancellor, Sandeep Giri, Founder, CloudX Labs.
REVA University’s REVA Academy for Corporate Excellence (RACE) has inked a memorandum of understanding with CloudxLab for setting up a Center of Excellence in AI and Deep Technologies and providing a platform for promoting research and innovation
REVA University and Cloudxlab research collaboration intends to work on technologies involving, deep learning, reinforced learning, curiosity-based machines, distributed computing, and launching specialized courses in these advanced technologies.
This collaboration will be aimed at providing and launching some highly sought-after courses in deep technologies involving experts from Academia as well as the industry. These courses will be delivered in hybrid mode – a combination of physical classroom, online instructor-led, self-paced, and project-based modes.
Dr. P. Shyama Raju, honorable Chancellor, REVA University said “This one-of-a-kind collaboration is aimed at being a launchpad for those who are planning to step into the world of AI, Deep Learning and other advanced technologies. It affirms REVA University’s commitment to make high-end technical education available to everyone in the world.”
“With Artificial Intelligence, machine learning, and other high-end technologies influencing every aspect of our lives, we are optimistic that this collaboration will help professionals in shaping their career”, says Sandeep Giri, CEO, and Founder at CloudxLab.
About REVA University
REVA University is one of the top-ranked private Universities in Bangalore, India, offering a wide range of UG, PG and PhD programs. REVA Academy for Corporate Excellence (RACE) is one of the initiatives of REVA University focused on corporate training to develop visionary enterprise leaders through progressive and integrated learning capabilities. RACE offers best-in-class, specialized, techno-functional, and interdisciplinary programs that are designed to suit the needs of working professionals.
If you are interested in Machine Learning or Deep Learning, but struggling to decide which book to use to study the same, here is a list of the best books in these fields. What makes this list even better is that some of these books are available online, for free! So go through the list, and pick the one that suits you best.
1. Deep Learning Book – by Aaron Courville, Ian Goodfellow, and Yoshua Bengio This book covers them all, including the mathematics required for Deep Learning. What’s more, it is available for free from the official website of this book. This is a must have for any serious Deep Learning practitioner.
Backpropagation is considered one of the core algorithms in Machine Learning. It is mainly used in training the neural network. And backpropagation is basically gradient descent. What if we tell you that understanding and implementing it is not that hard? Anyone who knows basic Mathematics and has knowledge of the basics of Python Language can learn this in 2 hours. Let’s get started.
Though there are many high-level overviews of the backpropagation and gradient descent algorithms what I found is that unless one implements these from scratch, one is not able to understand many ideas behind neural networks.
Recently, I came up with an idea for a new Optimizer (an algorithm for training neural network). In theory, it looked great but when I implemented it and tested it, it didn’t turn out to be good.
Some of my learning are:
Neural Networks are hard to predict.
Figuring out how to customize TensorFlow is hard because the main documentation is messy.
Theory and Practical are two different things. The more hands-on you are, the higher are your chances of trying out an idea and thus iterating faster.
I am sharing my algorithm here. Even though this algorithm may not be of much use to you but it would give you ideas on how to implement your own optimizer using Tensorflow Keras.
A neural network is basically a set of neurons connected to input and output. We need to adjust the connection strengths such that it gives the least error for a given set of input. To adjust the weight we use the algorithms. One brute force algorithm could be to try all possible combinations of weights (connections strength) but that will be too time-consuming. So, we usually use the greedy algorithm most of these are variants of Gradient Descent. In this article, we will write our custom algorithm to train a neural network. In other words, we will learn how to write our own custom optimizer using TensorFlow Keras.
GPT-3 is the largest NLP model till date. It has 175 billion parameters and has been trained with 45TB of data. The applications of this model are immense.
GPT3 is out in private beta and has been buzzing in social media lately. GPT3 has been made by Open AI, which was founded by Elon Musk, Sam Altman and others in 2015. Generative Pre-trained Transformer 3 (GPT3) is a gigantic model with 175 billion parameters. In comparison the previous version GPT2 had 1.5 billion parameters. The larger more complex model enables GPT3 to do things that weren’t previously possible.
In this blog we will show how to process video with YOLOv4 and tensorflow. YOLOv4 is out and it’s hot. YOLOv4 is significantly better than YOLOv3 as can be seen in the pic below.
In this blog we will show how to label custom images for making your own YOLO detector. We have other blogs that cover how to setup Yolo with Darknet, running object detection on images, videos and live CCTV streams. If you want to detect items not covered by the general model, you need custom training.
In our case we will build a truck type detector. There are 4 types of trucks we will try to identify
we will see how to setup object detection with Yolo and Python on images and video. We will also use Pydarknet a wrapper for Darknet in this blog. The impact of different configurations GPU on speed and accuracy will also be analysed.
This blog is part of series, where we examine practical applications of Yolo. In this blog, we will see how to setup object detection with Yolo and Python on images and video. We will also use Pydarknet a wrapper for Darknet in this blog. The impact of different configurations GPU on speed and accuracy will also be analysed.
We will explore YOLO for image recognition in a series of blogs. This is the first one. In this blog, we will see how to setup YOLO with darknet and run it. We will also demonstrate the various choices you have with YOLO in terms of accuracy, speed and cost, enabling you to make a more informed choice of how you would want to run your models.
Setup Yolo with Darknet
The content in the blog is not unique. However if you are starting with YOLO, this is the first thing you need to do.
