jppgks

toolchain-utilities

KnowHowDataset

s3cmd

Official s3cmd repo -- Command line tool for managing S3 compatible storage services (including Amazon S3 and CloudFront).

mssql-docker

Official Microsoft repository for SQL Server in Docker resources

CTranslate2

Fast inference engine for Transformer models

im2recipe

Code supporting the CVPR 2017 paper "Learning Cross-modal Embeddings for Cooking Recipes and Food Images"

ADA_Course_Project

LightGBM

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

click

Python composable command line interface toolkit

recipe-box

Scrape lists of recipes

visualise-spacy-tree

Create dependency tree plots from SpaCy Doc objects

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

interpret

Fit interpretable models. Explain blackbox machine learning.

fastText

Library for fast text representation and classification.

medgan

Generative adversarial network for generating electronic health records.

NLP-Cube

Natural Language Processing Pipeline - Sentence Splitting, Tokenization, Lemmatization, Part-of-speech Tagging and Dependency Parsing

noise2noise

Noise2Noise: Learning Image Restoration without Clean Data - Official TensorFlow implementation of the ICML 2018 paper

knockknock

🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

DeepFashion2

DeepFashion2 Dataset https://arxiv.org/pdf/1901.07973.pdf

multithreaded-estimators

Multithreading inference in Tensorflow Estimators. This is a ServiceNow Research project that was started at Element AI.

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

snorkel

A system for quickly generating training data with weak supervision

disentanglement_lib

disentanglement_lib is an open-source library for research on learning disentangled representations.

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

bert_language_understanding

Pre-training of Deep Bidirectional Transformers for Language Understanding: pre-train TextCNN

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

m3tl

BERT for Multitask Learning

BERT-AttributeExtraction

USING BERT FOR Attribute Extraction in KnowledgeGraph. fine-tuning and feature extraction. 使用基于bert的微调和特征提取方法来进行知识图谱百度百科人物词条属性抽取。

BERT-for-Semeval

Adapting Google's BERT model for the Semeval Hyperpartisan News Classifier Competition