pranavphoenix

Backbones

Clash of Backbones

BiLSTM-POS-Tagging

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

Cityscapes

Code to train Cityscapes Dataset with colour labels

CXV

Convolutional Xformers for Vision

Pix2Pix-Image-Video-Colourizing

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

TinyImageNetLoader

DataLoader for TinyImageNet Dataset

VisionXformer

Vision Xformers

WaveMix

2D discrete Wavelet Transform for Image Classification and Segmentation

WaveMixSR

Single Image Super Resolution Using WaveMix

WavePaint

Wavelet-based Image InPainting Model

pranavphoenix/WaveMix

2D discrete Wavelet Transform for Image Classification and Segmentation

pranavphoenix/WaveMixSR

Single Image Super Resolution Using WaveMix

pranavphoenix/CXV

Convolutional Xformers for Vision

pranavphoenix/WavePaint

Wavelet-based Image InPainting Model

pranavphoenix/VisionXformer

Vision Xformers

pranavphoenix/TinyImageNetLoader

DataLoader for TinyImageNet Dataset

pranavphoenix/Backbones

Clash of Backbones

pranavphoenix/BiLSTM-POS-Tagging

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

pranavphoenix/Cityscapes

Code to train Cityscapes Dataset with colour labels

pranavphoenix/FLD

Normalizing Flow based Evaluation Metric for Generative Models

pranavphoenix/FLD_plus

Normalizing Flow based Evaluation Metric for Generative Models

pranavphoenix/LSTM-sentiment-analysis

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

pranavphoenix/Model-Visualization

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

pranavphoenix/AI-OpenMic

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

pranavphoenix/BiLSTM-Chunking

Using Bi-LSTM for chunking of words in sentences

pranavphoenix/Convolutional-Xformers-for-Vision

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

pranavphoenix/CRF-Chunking

Using Conditional Random Fields to Chunk the words in a sentence

pranavphoenix/Dataloader

Dataloaders for standard datasets

pranavphoenix/DP2CP-Parser

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

pranavphoenix/DualOpt

Dual Optimizer Training

pranavphoenix/Easy2use

code snipets for easy access

pranavphoenix/ImageNet

ImageNet-1k Dataloader

pranavphoenix/Metrics

Metrics used for different computer vision tasks

pranavphoenix/Optimizer-lr-tuning

Analyze the performance of 7 optimizers by varying their learning rates

pranavphoenix/parameter_efficiency_leaderboard

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

pranavphoenix/pranavphoenix

pranavphoenix/pranavphoenix.github.io

Personal website

pranavphoenix/RL2

pranavphoenix/Transcribe

Transcribe using Whisper

pranavphoenix/WaveMix-Inpainting

Image inpainting using WaveMix model