Skip to main content

Ayush Thakur

ayush-thakur
Machine Learning Engineer at W&B
Weights and Biases
Kolkata
ayushthakur.gitbook.io
ayushthakur0
ayulockin/

Teams

Intro


Hello, I'm Ayush Thakur 👋

  • 🔭 I work at Weights and Biases as a Machine Learning Engineer.
  • 📣 I am a Google Developer Expert in Machine Learning (TensorFlow Core).
  • 🌻 I am a Kaggle Notebooks Master. Here's my Kaggle profile.
  • 🌱 I create content on deep learning. Please find some of my work down below.
  • 🪂 I build MLOps pipelines for open-source repositories like MMDetection, MMSegmentation, Keras, etc.
  • 🌞 Currently interested in Unsupervised Visual Representation Learning.
  • 👯 I would love to collaborate on any computer vision project. (It should not be face detection)
  • ✨ I love good discussions. Best way to reach me: Twitter - @ayushthakur0
  • 😄 Pronouns: He/His
  • ⚡ Fun fact: I love watching anime. (Naruto is all time fav. One Piece is love. Finally, Bleach is out. I can keep talking...)

Show some ❤️ by starring some of the reports!



Reports
Towards Deep Generative Modeling With Weight & Biases
In this article, we'll learn about Autoencoders and Variational Autoencoders and then dive into Generative Adversarial Modeling.
8074 views
Last edit 3 years ago
Interpretability in Deep Learning With Weights & Biases: CAM and Grad-CAM
This article reviews how Grad-CAM counters the common criticism that neural networks are not interpretable.
13096 views
Last edit 3 years ago
Generating Digital Painting Lighting Effects via RGB-space Geometry
Exploring the paper "Generating Digital Painting Lighting Effects via RGB-space Geometry" in which the authors propose an image processing algorithm to generate digital painting lighting effects from a single image.
22189 views
Last edit 3 years ago
An Introduction to Adversarial Latent Autoencoders
In this article, we harness the latent power of autoencoders, one disentanglement at a time, and provide an example that you can try for yourself.
26013 views
Last edit 2 years ago
Modern Data Augmentation Techniques for Computer Vision
A comparison between Cutout, mixup, CutMix, and AugMix augmentations and their impact on model robustness.
4553 views
Last edit 4 years ago
Simple Ways to Tackle Class Imbalance
This report explores various methods used to counter class imbalance in image classification problems – class weighting, oversampling, undersampling, and two-phase learning.
11707 views
Last edit 5 years ago
3D Image Inpainting With Weights & Biases
In this article, we take a look at a novel way to convert a single RGB-D image into a 3D image, using Weights & Biases to visualize our results.
30090 views
Last edit 2 years ago
Unsupervised Visual Representation Learning with SwAV
This article explores the SwAV framework, which is currently the SoTA in self-supervised learning for visual recognition.
15340 views
Last edit 3 years ago
An Overview of DeepFaceDrawing
This article provides an overview of DeepFaceDrawing, breaking down the key concepts and diving into this image-to-image translation technique.
8385 views
Last edit 2 years ago
Rewriting a Deep Generative Model: An Overview
In this article, we will explore the work presented in the paper "Rewriting a Deep Generative Model" by Bau et al. It shows a new way of looking at deep neural networks.
3816 views
Last edit 2 years ago
Model Card: NIH Chest X-ray Dataset
Model Card for binary classification of X-ray images.
2381 views
Last edit 5 years ago
Metric Learning for Image Search With Weights & Biases
In this article, we will explore supervised metric learning and extend it to image similarity search using Weights & Biases to track the results of our experiments.
3620 views
Last edit 3 years ago
Image Segmentation Using Keras and Weights & Biases
This article explores semantic segmentation with a UNET-like architecture in Keras and interactively visualizes the model's prediction using Weights & Biases.
6915 views
Last edit 2 years ago
Object Localization With Keras and Weights & Biases
This article explores object localization using the bounding box regression technique in Keras and interactively visualizes the model's prediction in Weights & Biases
5424 views
Last edit 2 years ago
SimpleTransformers: Transformers Made Easy
This article looks at SimpleTransformers, which removes the complexity and lets you get down to what matters – model training and experimenting with the Transformer model architectures.
10780 views
Last edit 2 years ago
From EMNIST to Wikisplit: Sentence Composition Using W&B
This article explains how to build a CNN+RNN model to read a sentence from an image, using Weights & Biases to track our experiments.
2843 views
Last edit 2 years ago
EMNIST Classification
Image classification on EMNIST/bymerge dataset.
3636 views
Last edit 5 years ago
In-Domain GAN Inversion for Real Image Editing
In this article, we explore a SOTA GAN Inversion technique proposed by the authors of In-Domain GAN Inversion and see some impressive GAN-based editing results.
5256 views
Last edit 2 years ago
Image Classification Using PyTorch Lightning and Weights & Biases
This article provides a practical introduction on how to use PyTorch Lightning to improve the readability and reproducibility of your PyTorch code.
28043 views
Last edit 1 year ago
An Overview of Instance Aware Image Colorization
This article explores an interesting learning-based image colorization technique that produces stunning colored images.
12718 views
Last edit 2 years ago
An Overview of Reduced-Precision Network for Image Reconstruction
This article explores a novel neural network architecture, QW-Net, which is a low-precision neural network for image reconstruction.
2011 views
Last edit 2 years ago
An Introduction to Egocentric Videoconferencing
This article explores a method for egocentric video conferencing that enables hands-free video calls, enabling you to better participate in video calls when on the move.
4550 views
Last edit 2 years ago
An Introduction to Training LLMs Using Reinforcement Learning From Human Feedback (RLHF)
In this article, we explore Reinforcement Learning from Human Feedback, a novel approach to reducing bias and increasing performance in large language models.
22659 views
Last edit 2 years ago
Understanding Reinforcement Learning from Human Feedback (RLHF): Part 1
This article on Understanding Reinforcement Learning from Human Feedback (RLHF) is part one of an ongoing review of important foundational papers by OpenAI in the alignment space.
58642 views
Last edit 5 months ago
Transfer Learning Using PyTorch Lightning
In this article, we have a brief introduction to transfer learning using PyTorch Lightning, building on the image classification example from a previous article.
17711 views
Last edit 2 years ago
How To Install TensorFlow With GPU Support on Windows
This article shows how to correctly install TensorFlow on a GPU-enabled system with a Windows operating system.
11984 views
Last edit 2 years ago
Multi-GPU Training Using PyTorch Lightning
In this article, we take a look at how to execute multi-GPU training using PyTorch Lightning and visualize GPU performance in Weights & Biases.
12753 views
Last edit 2 years ago
Dynamic Sky Replacement: The Sky Is Within Our Grasp!
This article explores an interesting paper called Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos.
4247 views
Last edit 2 years ago
How to save and load models in PyTorch
This article is a machine learning tutorial on how to save and load your models in PyTorch using Weights & Biases for version control.
122356 views
Last edit 11 months ago
How To Use GPU with PyTorch
A short tutorial on using GPUs for your deep learning models with PyTorch, from checking availability to visualizing usable.
270787 views
Last edit 9 months ago
An Intro to Retiming Instances in a Video
This article explores a method discussed in Layered Neural Rendering for Retiming People in Video. Using this, we can retime, manipulate, and edit motions, and more.
3967 views
Last edit 2 years ago
How to avoid checkerboard pattern in your generated images?
Getting rid of "checkerboard" artifacts with upsampling + convolutional layers.
7150 views
Last edit 4 years ago
Paper Summary: One Shot 3D Photography
This article explores a novel 3D photography method called 'One Shot 3D Photography' which uses a single 2D image to create stunning 3D photographs.
6917 views
Last edit 2 years ago
How to Evaluate GANs using Frechet Inception Distance (FID)
In this article, we will briefly discuss the details of GAN evaluation and how to implement the Frechet Inception Distance (FID) evaluation pipeline.
35680 views
Last edit 2 years ago
How to Correctly Install TensorFlow Object Detection API
Install TensorFlow Object Detection API on Windows 10 in 6 easy steps
13430 views
Last edit 4 years ago
X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation
This article briefly examines the X-Fields paper, proposing a novel method to seamlessly interpolate time, light, and view of a 2D image using X-Field.
4892 views
Last edit 2 years ago
Examples of Early Stopping in HuggingFace Transformers
In this article, we'll take a look at how to fine-tune your HuggingFace Transformer with Early Stopping regularization using TensorFlow and PyTorch.
18980 views
Last edit 2 years ago
Automating Animations with the Help of Robust In-Betweening
Using an adversarial neural network to automate animation
4244 views
Last edit 4 years ago
How To Fine-Tune Hugging Face Transformers on a Custom Dataset
In this article, we will learn how to easily fine-tune a HuggingFace Transformer on a custom dataset with Weights & Biases.
36225 views
Last edit 2 years ago
Taming Transformers for High-Resolution Image Synthesis
The efficiency of convolutional approaches with the expressivity of transformers.
9214 views
Last edit 2 years ago
An Introduction To The PyTorch View Function
Demystify the View function in PyTorch and find a better way to design models.
9039 views
Last edit 3 years ago
Exploring Adaptive Gradient Clipping and NFNets
A minimal ablation study of the proposed contributions in the latest High-Performance Large-Scale Image Recognition Without Normalization paper.
4730 views
Last edit 4 years ago
One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing
In this report, we will look at the latest work published in CVPR 21 in the domain of one-shot talking-head synthesis.
9609 views
Last edit 4 years ago
Train Generative Adversarial Networks (GANs) With Limited Data
In this report, we'll learn about the adaptive discriminator augmentation technique that enables us to train GANs with a limited training dataset
3664 views
Last edit 4 years ago
What's New in Computer Vision?
A hand curated list of recent developments in computer vision that I find interesting.
1221 views
Last edit 4 years ago
What's the Optimal Batch Size to Train a Neural Network?
We look at the effect of batch size on test accuracy when training a neural network. We'll pit large batch sizes vs small batch sizes and provide a Colab you can use.
50480 views
Last edit 2 years ago
How To Check If PyTorch Is Using The GPU
In this tutorial, we walk you through how to check if PyTorch is using your GPU.
46977 views
Last edit 3 years ago
Predicting Lung Disease with Binary Classification on the NIH Chest X-ray Dataset
In this report, we will perform binary classification on the NIH Chest X-ray dataset.
2808 views
Last edit 3 years ago
What's the best data representation and the effect of Mixup?
Experiments to answer some key questions for the SETI Breakthrough Listen - E.T. Signal Search Kaggle competition.
444 views
Last edit 3 years ago
Overview: Neural Scene Flow Fields (NSFF) for Space-Time View Synthesis of Dynamic Scenes
This report summarizes the proposed approach to create a novel view and time synthesis of dynamic scenes, using only a monocular video with known camera poses as input.
3148 views
Last edit 3 years ago
ReLU vs. Sigmoid Function in Deep Neural Networks
ReLU vs. Sigmoid Function in Deep Neural Networks: Why ReLU is so Prevalent? What's all the fuss about using ReLU anyway?
50632 views
Last edit 1 year ago
How to Handle Images of Different Sizes in a Convolutional Neural Network
Datasets come in all shapes and sizes. CNNs don't like that. Here's how to make it work (with code).
54767 views
Last edit 3 years ago
Comparing Sigmoid-MSE With Softmax Cross-Entropy for Image Classification
In this article, we look at the results from an experiment to compare sigmoid with MSE and softmax with cross-entropy for image classification.
5650 views
Last edit 2 years ago
How To Use Weights & Biases With MMDetection
In this article, we'll train an object detection model using MMDetection and learn how to use MMDetWandbHook to log metrics, visualize predictions, and more.
9088 views
Last edit 2 years ago
PyTorch Dropout for regularization - tutorial
Learn how to regularize your PyTorch model with Dropout, complete with a code tutorial and interactive visualizations
119158 views
Last edit 10 months ago
Implementing and Tracking the Performance of a CNN in PyTorch
This article provides a guide to implementing and tracking the performance of a Convolutional Neural Network (CNN) in PyTorch.
6168 views
Last edit 3 years ago
Using GPUs With Keras: A Tutorial With Code
This tutorial covers how to use GPUs for your deep learning models with Keras, from checking GPU availability right through to logging and monitoring usage.
29469 views
Last edit 2 years ago
Batch Normalization in Keras - An Example
Implementing Batch Normalization in a Keras model and observing the effect of changing batch sizes, learning rates and dropout on model performance.
24283 views
Last edit 3 years ago
Modern Data Augmentation Techniques for Computer Vision
This article gives a comparison between Cutout, mixup, CutMix, and AugMix augmentations, and their impact on model robustness.
7558 views
Last edit 3 years ago
Understanding the Effectivity of Ensembles in Deep Learning
In this article, we dissect ensembles in order to provide different insights that are useful for understanding the dynamics of deep neural networks in general.
7844 views
Last edit 3 years ago
How One-Hot Encoding Improves Machine Learning Performance
A brief discussion of one-hot encoding, where best to use it, and why it works
5118 views
Last edit 4 years ago
How to Prevent TensorFlow From Fully Allocating GPU Memory
In this report, we see how to prevent a common TensorFlow performance issue
11224 views
Last edit 3 years ago
Input Keras Layer Explanation With Code Samples
Simple answers to common questions related to the Keras layer arguments, including input shape, weight, units and dim. With examples.
61523 views
Last edit 1 year ago
LSTM RNN in Keras: Examples of One-to-Many, Many-to-One & Many-to-Many
In this report, I explain long short-term memory (LSTM) recurrent neural networks (RNN) and how to build them with Keras. Covering One-to-Many, Many-to-One & Many-to-Many.
66270 views
Last edit 2 years ago
A Guide to Multi-Label Classification on Keras
In this article, we explore the necessary ingredients for multi-label classification, including multi-label binarization, output activation, and loss functions.
18527 views
Last edit 2 years ago
How to Fine-Tune HuggingFace Transformer with W&B
In this report, we will learn how to easily fine-tune a HuggingFace Transformer on a custom dataset.
2895 views
Last edit 4 years ago
Use Mixed Precision Training
Double your batch size with mixed precision.
673 views
Last edit 4 years ago
TensorFlow suddenly not detecting GPU on my GCP VM
1487 views
Last edit 4 years ago
Integrating Keras with Weights & Biases
A step-by-step tutorial where we'll train a simple image classifier and show you how to use Weights & Biases in your Keras projects
5211 views
Last edit 2 years ago
What's the Difference Between Strided Convolution and Pooling?
In this article, we'll do a quick comparison of the benefits and detriments of two different ways to downscale input tensor: pooling and strided convolutions.
5897 views
Last edit 2 years ago
Image Classification Using Vision Transformer and KerasCV
In this article, we'll learn how to use KerasCV to fine-tune a vision transformer (ViT) on our custom dataset. We also provide code so that you can follow along.
5963 views
Last edit 2 years ago
Keras Dense Layer: How to Use It Correctly
In this article, we'll look at the Dense Layer in Keras so that you can build a thorough understanding that will be vital when building custom models in Keras.
36173 views
Last edit 2 years ago
How to Evaluate, Compare, and Optimize LLM Systems
This article provides an interactive look into how to go about evaluating your large language model (LLM) systems and how to approach optimizing the hyperparameters.
26532 views
Last edit 1 year ago
Building Advanced Query Engine and Evaluation with LlamaIndex and W&B
This report showcases a few cool evaluation strategies and touches upon a few advanced features in LlamaIndex that can be used to build LLM-based QA bots. It also shows, the usefulness of W&B for building such a system.
15768 views
Last edit 2 years ago
How to Use Cosine Decay Learning Rate Scheduler in Keras
In this article, we'll learn how to use cosine decay in Keras, providing you with code and interactive visualizations so you can give it a try it for yourself.
8438 views
Last edit 2 years ago
Intuitive understanding of 1D, 2D, and 3D convolutions in convolutional neural networks.
This report will try to explain the difference between 1D, 2D and 3D convolution in convolutional neural networks intuitively.
27044 views
Last edit 4 years ago
HPA: Visualize Segmentation Masks
This report is meant to showcase the cell segmentation masks generated using the HPA-Cell-Segmentation tool for Human Protein Atlas - Single Cell Classification competition.
669 views
Last edit 4 years ago
Projects
Links
Activity
Mon
Wed
Fri
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Runs
Name
Project
State
Created
No rows found
Loading...