Cloudwalker

Personal website

Wavelet-based Image InPainting Model

2D discrete Wavelet Transform for Image Classification and Segmentation

Using Pix2Pix Conditional GAN architecture to colourize image using Places365 dataset and use that model to colourize video clips

Clash of Backbones

Vision Xformers

Single Image Super Resolution Using WaveMix

code snipets for easy access

Dual Optimizer Training

DataLoader for TinyImageNet Dataset

No description provided.

Normalizing Flow based Evaluation Metric for Generative Models

Transcribe using Whisper

Normalizing Flow based Evaluation Metric for Generative Models

No description provided.

Convolutional Xformers for Vision

We use Bi-LSTM to learn to tag the Parts of Speech in a sentence using NLTK Brown corpus Dataset.

Visualize Vision Models by looking at Kernel Maps, Outputs in each layer and Occlusion Analysis

Image inpainting using WaveMix model

Code to train Cityscapes Dataset with colour labels

Metrics used for different computer vision tasks

Dataloaders for standard datasets

The most parameter efficient machine learning models on a few popular benchmarks

ImageNet-1k Dataloader

Convolutional Xformers for Vision (CXV) are hybrid models that use both convolutional and linear transformers for Computer Vision Applications

Repository for code and dataset for our EMNLP 2021 paper - “So You Think You’re Funny?”: Rating the Humour Quotient in Standup Comedy.

Using LSTM for sentiment analysis of IMDB movie reviews and using GloVe Embeddings for analogy tasks

Analyze the performance of 7 optimizers by varying their learning rates

Creating Constituency Parse tree of a simple sentence given its Dependency Parsing

Using Conditional Random Fields to Chunk the words in a sentence