Palaash Agrawal's repositories
Acads-BITSPilani
Term Project based on the paper "Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction" by Maosin Li et al (2020, CVPR). A basic innovation added
NSD_exploration
Exploration of the Natural Scenes Dataset
v1-Fake-Speech-Detection-using-Frequncy-analysis
A CNN that can differentiate between Donald Trump's real voice and voices of Impressionists using frequency analysis of hand-curated audio snippets
Which-celebrity-do-you-look-like
My personal rendition of the facial recognition problem using Siamese Network. Inspired by the Gradient App
Brain-MRI-Segmentation
A UNet Segmentation model to detect FLAIR abnormality in the brain
Contour-Descent-Optimizer
A novel optimization method to accelerate the Gradient Descent Algorithm by manifold
course-v3
The 3rd edition of course.fast.ai
fastai
The fastai deep learning library
fastai-v3
Starter app for fastai v3 model deployment on Render
fastai2
Temporary home for fastai v2 while it's being developed
fastbook
Draft of the fastai book
imagenet_experiments
Experiments on blurred image transforms on the image recognition task over Imagenet
learning_new_stuff
A repo where I learn to implement fundamental concepts in Deep Learning by implementing it in code.
metrabs
Estimate absolute 3D human poses from RGB images.
PalaashAgrawal.github.io
Palaash Agrawal's personal website
practicals
Practical Machine Learning, hosted at palaashagrawal.github.io/practicals
prepositions1.0
Baseline model experiments for prepositions paper submitted to CVPR
STUPD
Code for the STUPD paper
v2-Fake-Speech-Detection-using-Fequency-Analysis
A CNN that classifies whether an audio segment is spoken by Donald Trump himself, or Impersonated.