Photo by ThisisEngineering RAEng on Unsplash

Optimization means improving the performance of a system. How you measure the performance is based on the scenario, it might be accuracy, speed, power consumption or something else. Generally, you can take two approaches to increase the performance of your system. You can use Hardware Optimization, or you can use Software Optimization. Let’s say you have a desktop from 2009 when it was mediocre for its time. Now in 2021, the performance of that system (speed) might not be good enough for you. So you might decide to upgrade the CPU, memory or other parts of your machine, which is…

Photo by Christina @ on Unsplash

Everybody codes differently. There are no hard and fast rules of how you must approach a problem, how you should implement it, however there are some certain standards. Often, you will be working on a team, or might be working in an open source project where many others will work on the same program with you. Your code might even be used as production code. So there needs to be a certain standards to follow.

Data scientists might come from different backgrounds. I, for example, came from a background that had nothing to do with programing. And so while working…

Photo by William Choquette from Pexels

Training a deep neural network requires high computational resources, specially very high end GPUs. But building such a powerful machine is very costly and may not be viable for many cases. Here comes the cloud service providers like AWS (Amazon), GCP (Google), Azure (Microsoft) to the rescue. They provide powerful virtual machines in the cloud which comes with all the drivers and most of the popular deep learning software and frameworks pre-installed so that you don’t need to worry about setting up anything by yourself. …

Photo by Jan Laugesen on Unsplash

NumPy is a very powerful tool for numerical calculation in large data set. It’s a python library which has many built-in methods for performing fast vectorized array operations. NumPy can be used to perform complex computations on entire array without the need for Python for loops and it is significantly more efficient in memory use than their pure python counterparts. In this post I will talk about some basic ways of creating numpy arrays and then some common operations and how we can use them for efficient performance. You can find all the codes in my github repository here where…

Photo by Joshua Melo on Unsplash

In my previous posts, I have introduced OpenVINO, described how to install it in windows computer, how to process input and output and how to get a model or prepare one in model optimizer. We are now at the final step, performing the inference with the inference engine. So lets begin. The discussed topics in this post are,

  • Inference Engine
  • Feeding a model to the inference engine
  • Checking for unsupported layers and using CPU extension (deprecated)
  • Sending inference request
  • Handling the output
  • Integrating into an app

Inference Engine

Inference engine runs the actual inference on a model. In part 1, we have…

Photo by Drew Patrick Miller on Unsplash

In part 1, I talked about how to download a pretrained model which was already optimized for using in openVINO toolkit. In this part, we will see how to optimize an unoptimized model by the model optimizer. Topics that will be covered in this post are,

  • Optimization techniques
  • Supported frameworks
  • Intermediate Representation
  • Converting ONNX model
  • Converting Caffe model
  • Converting TensorFlow model

How Optimization Is Done

Model optimizer is a command line tool that converts a model, made using a supported framework, into an intermediate representation which can be used in the inference engine. The model optimizer is a python file named “”

In my previous blog, I briefly talked about AI at the edge application and introduced Intel OpenVINO toolkit. In this post, I will talk about obtaining a pre-trained model from OpenVINO’s model zoo and how to leverage it in your app. The topics that will be covered in this post are,

  • Different Computer Vision model types
  • Available Pre-Trained Models in the Software
  • Downloading a pre-trainned model with the model downloader
  • Deploying a Basic App with the Pre-Trained Model

Different Computer Vision Models

There are several types of computer vision models that serves different purposes. …

We now live in the age of cloud computing. Everything is on the cloud now, Your data, your processing power- everything. Cloud services like AWS, Azure, GCP etc have made it very easy for your IoT devices to make up for the lack of processing power in local machine and use the processing power in the cloud and serve you with the amazing capability of AI. But not in every case, you can rely to cloud services. There is always a risk of leaking your sensitive personal data if you send it to the cloud. There might be network issue…

Windows 10 lock screen

Windows 10 has a great feature called Windows spotlight that automatically updates your lock screen background with amazing photos. Unfortunately, there is no built-in way to put them in your desktop background too. And the image files are saved in the deepest part of the jungle of windows file system. So it’s pretty hard to find where they are. Manually copying them to your preferred directory is possible, but you have to copy the files and rename them to add the .jpeg extension in order to make them work with any photo opening app. I guess you get the idea…

Photo by Anete Lūsiņa on Unsplash

Traveling is fun. You get to see new places, meet new people, learn new culture, their heritage and what not. If you are a photographer, you get amazing scenery to shoot great pictures too! But travel comes with a boring part- preparing for the journey. I have hardly seen anyone who is excited about packing their bag. But you need to do some careful preparation to ensure that your bag is not weighted too much, which becomes a burden to carry or you need to make sure you are not short in anything that you need in your travel.


Nazmul Ahsan

I graduated as an Material Engineer, working as a Software Engineer and highly passionate about Artificial Intelligence

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store