pengKiina

KeypartX

KeypartX is a graph-based approach to represent perception (text in general) by key parts of speech.

autocorrect

Spelling corrector in python

CLIP

Contrastive Language-Image Pretraining

contextualSpellCheck

✔️Contextual word checker for better suggestions

coreferee

Coreference resolution for English, French, German and Polish, optimised for limited training data and easily extensible for further languages

Deep-Learning-Framework-for-Multi-modal-Product-Classification

Code repository for Rakuten Data Challenge: Multimodal Product Classification and Retrieval.

EasyOCR

Ready-to-use OCR with 40+ languages supported including Chinese, Japanese, Korean and Thai

emoji

emoji terminal output for Python

ETDataset

The Electricity Transformer dataset is collected to support the further investigation on the long sequence forecasting problem.

FaceLib

Face Detection & Age Gender & Expression & Recognition

gemoji

Info on GitHub emoji: gemoji

holbertonschool-machine_learning

This repository contains directories pertaining to the Machine Learning Specialisation curriculum at Holberton. Python: 100%.

Informer2020

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

instagram-scraper

Scrapes an instagram user's photos and videos

InstaLooter

Another API-less Instagram pictures and videos downloader.

leidenalg

Implementation of the Leiden algorithm for various quality functions to be used with igraph in Python.

mmaction2

OpenMMLab's Next Generation Action Understanding Toolbox and Benchmark

mmf

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

mml-book.github.io

Companion webpage to the book "Mathematics For Machine Learning"

Multi-Modal-classification-by-using-Image-Text-dataset

Multimodal-Deep-Learning-for-Music-Genre-Classification

Using the Million Song Dataset, genre tags from Last.fm, and lyrics from Musixmatch, I constructed a multi-genre classifier that can effectively detect both single genres and fusion genres of tracks, using a dataset crafted from multiple modalities.

Multimodal-Meme-Classification-Identifying-Offensive-Content-in-Image-and-Text

Multimodal Meme Classification: Identifying Offensive Content in Image and Text

Multimodal-Toolkit

Multimodal model for text and tabular data with HuggingFace transformers as building block for text data

Multimodal-Transformer

[ACL'19] [PyTorch] Multimodal Transformer

multimodal_social_media

multimodal social media content (text, image) classification

pengKiina

Config files for my GitHub profile.

pyvis

Python package for creating and visualizing interactive network graphs.

research

word_forms

Accurately generate all possible forms of an English word e.g "election" --> "elect", "electoral", "electorate" etc.

yolov4-deepsort

Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.