Open in app

Sign In

Write

Sign In

Sushant Gautam
Sushant Gautam

72 Followers

Home

About

Pinned

Simple and Intuitive Explanation of YOLO

Explore the fundamentals of YOLO and mathematical loss functions with annotated paper and summary. YOLO (“You Only Look Once”) is an effective real-time object recognition algorithm, first described in the seminal 2015 paper by Joseph Redmon et al. …

Yolo

6 min read

Simple and Intuitive Explanation of YOLO
Simple and Intuitive Explanation of YOLO
Yolo

6 min read


Published in The Startup

·Pinned

How to Make Real-Time Handwritten Text Recognition With Augmentation and Deep Learning

Use Convolutional Recurrent Neural Network to recognize the Handwritten line text image without pre segmentation into words or characters. Use CTC loss Function to train. What is covered here: Offline Handwritten Recognition Understand the detailed architecture of the Handwritten Recognition system. How to use the Data Augmentation technique to increase…

Deep Learning

6 min read

How to Make Real-Time Handwritten Text Recognition With Augmentation and Deep Learning
How to Make Real-Time Handwritten Text Recognition With Augmentation and Deep Learning
Deep Learning

6 min read


Feb 8

Will Google Bard become a new ChatGPT rival?

Bard seeks to combine the breadth of the world’s knowledge with the power, intelligence, and creativity of our large language models — Sundar Pichai Google launched Bard, its own language-based conversational AI, in the midst of a controversy about how AI is being utilized more and more. Chat GPT is…

Chatgpt

3 min read

Will Google Bard become a new ChatGPT rival?
Will Google Bard become a new ChatGPT rival?
Chatgpt

3 min read


Dec 8, 2022

DatasetGAN: Create huge Synthetic dataset with few human annotation

Walk through the essential ideas, along with their explanations. Current deep networks are extremely data-hungry, benefiting from training on large-scale datasets, which are time consuming to annotate and expensive too. So, DatasetGAN only needs a few labeled examples to learn how to generalize. This makes it possible to create an…

Gans

4 min read

DatasetGAN: Create huge Synthetic dataset with few human annotation
DatasetGAN: Create huge Synthetic dataset with few human annotation
Gans

4 min read


Nov 23, 2022

Secrets behind Vision Transformer that surpass CNN performance

Go through the vision transformer architecture, concepts, and major steps Vision transformers (ViTs) extract patches from images and feed them into a transformer encoder to obtain a global representation, which will finally be transformed for classification. The main idea is how we can use a transformer for image classification tasks…

Transformer

4 min read

Secrets behind Vision Transformer that surpass CNN performance
Secrets behind Vision Transformer that surpass CNN performance
Transformer

4 min read


Jan 14, 2022

Hidden secret behind SinGAN that won the ICCV 2019 best paper award

Explanation of SinGAN’s operation, architecture, and key principles, including mathematical equation details. You’re astounded, aren’t you? With a single training image, it is possible to generate realistic image creation, in contrast to deep GAN, which requires a significant amount of data. In this post, we will look into the SinGAN…

Deep Learning

7 min read

Hidden secret behind SinGAN that won the ICCV 2019 best paper award
Hidden secret behind SinGAN that won the ICCV 2019 best paper award
Deep Learning

7 min read


Jan 13, 2022

A Simple and Intuitive Explanation of StackGAN.

Walkthrough StackGAN formulation, concepts, and equation in great detail. Isn’t it a fascinating result? GAN creates output according to the text description you provide. Let’s see how StackGAN generates that output in a simple way. You will not be bored, believe me. StackGAN synthesizes photo-realistic images from text descriptions in…

Computer Vision

7 min read

A Simple and Intuitive Explanation of StackGAN.
A Simple and Intuitive Explanation of StackGAN.
Computer Vision

7 min read


Jan 7, 2022

HOW ProGAN WOKS?

The understanding basic intuition behind Progressive Growing of GANS. — ProGAN stands for 𝑷𝒓𝒐𝒈𝒓𝒆𝒔𝒔𝒊𝒗𝒆 𝑮𝒓𝒐𝒘𝒊𝒏𝒈 𝒐𝒇 𝑮𝑨𝑵𝒔. This is a significant contribution to GANS. Researchers at Nvidia implement this concept where GANs grow progressively during training to generate large resolution images (e.g. 1024x1024) and presented at the 6th International Conference on Learning Representations (ICLR). …

Computer Vision

6 min read

HOW ProGAN WOKS?
HOW ProGAN WOKS?
Computer Vision

6 min read


Published in Towards AI

·Dec 16, 2021

Basic Intuition And Guide to Neural Style Transfer

Simple explanation behind the idea of neural style transfer and implementation with PyTorch. Introduction Neural Style Transfer, in short NST, is an interesting idea where neural networks learn to transfer style i.e. it learns how to paint and generate a new image with a unique painting. The concept of style transfer…

Deep Learning

7 min read

Basic Intuition And Guide to Neural Style Transfer
Basic Intuition And Guide to Neural Style Transfer
Deep Learning

7 min read


Published in Towards AI

·Oct 19, 2021

The Intuition Behind GANs for Beginners

You have probably heard about deep fake videos or visit thispersondoesnotexit, where GAN is used to create those. Isn’t that Interesting. In this post, we will discuss the basic intuition behind GAN in-depth, its implementation in Tensorflow. Let’s get started. Generative Adversarial Networks, in short, GAN are an approach to…

Deep Learning

7 min read

The Intuition Behind GANs for Beginners
The Intuition Behind GANs for Beginners
Deep Learning

7 min read

Sushant Gautam

Sushant Gautam

72 Followers

Interest in Computer Vision, Deep Learning Research.

Following
  • Jonathan Hui

    Jonathan Hui

  • Harald Scheidl

    Harald Scheidl

  • Andrew Ng

    Andrew Ng

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech