Ankit Shah's Projects
Solutions to https://dailycodingproblem.com
Code and model for the DAISY shooter localization system
The Dakshina dataset is a collection of text in both Latin and native scripts for 12 South Asian languages. For each language, the dataset includes a large collection of native script Wikipedia text, a romanization lexicon of words in the native script with attested romanizations, and some full sentence parallel data in both a native script of the language and the basic Latin alphabet.
moDel Agnostic Language for Exploration and eXplanation
YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
Repository of teaching materials, code, and data for my data analysis and machine learning projects.
Cheat Sheets
A curated list of data science blogs
Data-Structures using C++.
Collection of papers and resources for data augmentation for NLP.
A parallel iterator for large machine learning datasets that don't fit into memory inspired by PyTorch's `DataLoader` class. https://lorenzoh.github.io/DataLoaders.jl/dev
Open Source Data Science Resources.
The Open Images dataset
Dataset Distillation
CMU Document Grounded Conversation Dataset
CMU Wilderness Multilingual Speech Dataset
A Streamlit app to add structured tags to the datasets
Viewer for the 🤗 datasets library.
The Leek group guide to data sharing
Code related to "Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity" paper
DCASE 2017 Baseline system
code for our 1st prize system to win the DCASE2017 task4 challenge
DCASE 2018 Baseline system
MobileNetV2-based baseline system for DCASE2021 Challenge Task 2.
The code for DCASE2021 task5 submission.