Machine Learning @ Quinnox | Love to write about Deep Learning for NLP and Computer Vision, Model Deployment, and ReactJS.

Computer Vision, Deep Learning

A CNN free GAN network

Image for post
Photo by Daniel McCullough on Unsplash

Most of the NLP tasks are currently solved using the Transformer network or a variation in the Transformer network. Transformers have become an integral part of the NLP eco-system over the past few years because of their reusability. Some multi-modal tasks are using the transformer network somewhere; still, those aren’t CNN free. Any Computer Vision task coupled with Transformers; also employs a CNN as backbones for feature extraction. But with TransGAN, a pure transformer network-based architecture is developed to train a GAN for image synthesis. …

Computer Vision

Deep Learning way to search images

Image for post
Photo by Maria Teneva on Unsplash

Recently, the researchers at OpenAI published a multi-modal architecture that can be used for 30 different tasks once pre-trained on around 400 million image-text pairs. This methodology isn’t that new previously many other researchers have tried to use a combination of Text Transformer and Pre-Trained CNN model to pre-train a model on Image-Text pairs and then use it on different downwards tasks. But for varieties of reasons those approaches weren’t that successful as discussed in the paper. A variety of pre-training approaches were tried, both predictive and contrastive; to achieve SOTA level accuracy on different downwards tasks. In the predictive…

A hands-on guide on

A hassle free approach to deploy Image models

Image for post

In this blog, we will try to deploy a Multi-Label Image Classifier using Streamlit. Every Deep Learning practitioner knows it’s very tedious to deploy Deep Learning model with Image input. With text, it’s easy as the input text can be easily passed into a JSON via the API call but with images, there are some few extra steps involved. When passing an image as an input via the API request it should be first converted either to a base64 string or it should be uploaded to a bucket directly from the UI and the link of that image should then…

Deep Learning, Programming

An effortless way to publish data apps to the internet.

Image for post

Deep Learning and Machine Learning models trained by many data professionals either end up in an inference.ipynb notebook or an app.pyfile 😅. Those meticulous model architectures capable of creating awe in the real world never see the light of the day. Those models just sit there in the background processing requests via an API gateway doing their job silently and making the system more intelligent.

People using those intelligent systems don’t always credit the Data Professionals who spent hours or weeks or months collecting data, cleaning the collected data, formatting the data to use it correctly, writing the model architecture…

Image for post

In this blog, we will be looking at one more way to leverage the Self-Attention Transformer model to classify a piece of text into two different categories each category containing some number of classes. Here, we will have two decoders and one encoder wherein the encoder will extract the question features and pass it to the first decoder with [CLS] index and then pass the encoder features to the second decoder with the class index for that question. …

Image for post

In this blog, we will go through one of how we can use Self-Attention Transformer models to classify a piece of text (question in our case) into two different categories each category containing some number of classes.

We will look at a Self-Attention Transformer with multiple heads for classifying classes in different categories. Without any further adieu let’s code out the Encoder and Decoder modules for a Multi-Head Self-Transformer to classify multiple labels via multiple fully connected linear layer. The Encoder and Decoder parts will be similar to the once shown in Part — 1.1. You can use that same…

Image for post

Understanding the Multi-Head Self-Attention Transformer network with code in PyTorch

In this part of the blog series, we will be trying to understand the Encoder-Decoder architecture of the Multi-Head Self-Attention Transformer network with some code in PyTorch. There won’t be any theory involved(better theoretical version can be found here) just the barebones of the network and how can one write this network on its own in PyTorch.

The architecture comprising the Transformer model is divided into two parts the Encoder part and the Decoder part. Several other things combine to form the Encoder and Decoder parts. Let’s start with the Encoder.


The Encoder part is quite simpler compared to the…

Image for post

This series of blogs will go through the coding of Self-Attention Transformers from scratch in PyTorch, Text Classification using the Self-Attention Transformer in PyTorch, and Different Classification strategies to solve classification problems with multiple categories with each category having some number of classes. This series is divided into four parts

Image for post

This is the second blog in the series Deploying a Multi-Label Image Classifier using PyTorch, Flask, ReactJS and Firebase data storage. If you missed the first blog its here. Before, starting with this blog be sure to go through the previous one.

In this blog we will be developing a flask app/service to create an API for our ReactJS front-which we will be building in next part.

The whole code base is shared here.

1. Installing the required modules

Go to your Unix/Linux based terminal and use the following line to install the required modules. …

Image for post

This is the first blog from the series of blogs based on building deep learning models and taking them to production.

The code included in the blog post can be found here.

1. Introduction to Multi-Label Image Classification and the Image dataset

Let’s define Multi-Label classification, we can consider this problem of multi-label classification as Multiple Binary Class Classification. In layman’s terms, supposedly, there are 20 different class labels in a dataset of images. Any image in the dataset might belong to some classes and those classes depicted by an image can be marked as 1 and the remaining classes can be marked as 0. …

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