Ankit Shah's Projects
Learned Perceptual Image Patch Similarity (LPIPS) metric. In CVPR, 2018.
PerfView is a CPU and memory performance-analysis tool
Joint Detection and Identification Feature Learning for Person Search
List of Hackathon Hackers' personal sites.
Code for performing 3 multitask machine learning methods: deep neural networks, Multitask Multi-kernel Learning (MTMKL), and a hierarchical Bayesian model (HBLR).
Datasets for Deep learning Personas
Person Finder is a searchable missing person database written in Python and hosted on App Engine.
Deep neural network model introducing new novel matching layer called 'Normalized correlation' layer. This repository contains information about the datasets used, implementation code for our NIPS-2016 paper "Deep Neural Networks with Inexact Matching for Person Re-Identification"
PostgreSQL Tools Service that provides PostgreSQL Server data management capabilities.
PhiNet module for PyTorch and PyTorch Lightning.
PHYRE is a benchmark for physical reasoning.
The end-to-end platform for building voice products at scale
100Gbps Intrusion Detection and Prevention System
Image-to-Image Translation with Conditional Adversarial Networks (Pix2pix) implementation in keras
The Places365-CNNs for Scene Classification
Learning Latent Dynamics for Planning from Pixels
PyTorch code for "Play It Back: Iterative Attention for Audio Recognition"
Paddle Large Scale Classification Tools
"Probabilistic Machine Learning" - a book series by Kevin Murphy
Out-of-distribution detection using the pNML regret. NeurIPS2021
On-device wake word detection powered by deep learning.
Code repository for Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper https://arxiv.org/abs/1807.04067
Human Pose estimation with TensorFlow framework
Pothole detection via Mask Rcnn
Praat: Doing Phonetics By Computer
A python library for working with praat, textgrids, time aligned audio transcripts, and audio files. It is primarily used for extracting features from and making manipulations on audio files given hierarchical time-aligned transcriptions (utterance > word > syllable > phone, etc).