Neural network quantization is a process of reducing the precision of the weights in the neural network, thus reducing the memory, computation, and energy bandwidths.
Particularly when deploying NN models on mobile or edge devices, quantization, and model compression in general, is desirable and often the only plausible way to deploy a mobile model as the memory and computational budget of these devices is very limited.
Continue reading “Neural Network Quantization Research Review”
The Model Maker library makes the process of developing TF Lite models quick and easy. It also allows you to adopt different architectures for your models.
The process of exporting the TF Lite models is also straightforward. Let’s take a look at how you can do that for image classification models.
Continue reading “TensorFlow Lite Image Classification Models with Model Maker”
The recent improvements in the field of speech synthesis have lead to many innovative technologies, offering a wide range of useful applications like automatic speech recognition, natural speech synthesis, voice cloning, digital dictation, and so forth.
Deep learning has played an immensely important role in improving already existent speech synthesis approaches by replacing the entire pipeline process with neural networks trained on data alone.
Continue reading “An architecture for production-ready natural speech synthesizer”
Building a machine learning model to identify custom images might require a lot of dataset collection and a lot of time to do it correctly.
This article is not a theoretical one—rather, I’ll walk you through the steps for creating an app that you could distribute amongst your peers to collect, create, and analyze TensorFlow models.
If you want a custom image classifier, but don’t have the right data or the know-how to build it, you’ve come to the right place.
Quantization can make your deep learning models smaller, faster, and more energy-efficient (I’ve written about this previously).
But the process may cause high accuracy loss or may not improve prediction speed if done incorrectly. So here, I’m sharing some practical tips to minimize accuracy loss while maintaining good inference speed. These points are valid for both post-training quantization and quantization-aware training.
Continue reading “Practical tips for better quantization results”
So I just had a brief chat with Elon Musk about his SpaceX program. I also discussed life and its meaning with Socrates.
I’m not joking – it’s real and all this is possible with artificial intelligence. I’m talking about a chatbot service called Character AI where you can chat with your favorite characters.
There are many chatbot services in the market but with Character AI, it’s like you’re actually chatting with the character you choose.
Continue reading “Character AI Review (2024): A New Realm of Imagination”
Computer scientists have been attempting to solve many different Natural Language Processing (NLP) problems since the time computers were conceived.
But the field become slightly stagnant around the 2000s, and did not gain traction again till the ‘Deep Learning’ boom that occurred during the last decade.
Of the many factors that helped build this traction was the spike in available textual data, thanks to the rise in the number of web and mobile applications.
Continue reading “Five Contemporary Natural Language Processing Problems Pushed Forward by DL”
Adding a colorful gradient is a great way to build backgrounds and create even more impressive filters. In Facebook’s Spark AR Studio, we use the Patch Editor to create color gradients.
In this article, we will learn to create a colorful gradient, add a gradient to the whole scene, and to a distance field shape. Follow the steps below to create colorful gradients in the Patch Editor.
Continue reading Add Color Gradients To Materials in Facebook’s Spark AR Studio
In a previous article — Build iOS-ready machine learning models using Create ML—we learned how to create and train our own Core ML model using Xcode.
Then, we learned how to fine-tune these custom models to provide accurate results. For that, check out the following tutorial: Create ML — Increasing ML model accuracy.
Continue reading “Building a multi-class image classifier on iOS”
At WWDC 18, Apple announced Create ML, a platform to create and train custom machine learning models on your Mac. You can train models to perform tasks like image recognition, extracting meaning from text, or finding relationships between numerical values.
Continue reading “Working with Create ML’s MLDataTable to Pre-Process Non-Image Data”
