tskatom Goto Github PK

pystruct

Simple structured learning framework for python

pytext

A natural language modeling framework based on PyTorch

python-100-days

Python - 100天从新手到大师

python-patterns

A collection of design patterns/idioms in Python

pytorch-gan

PyTorch implementations of Generative Adversarial Networks.

pytorch-lightning

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

pytorch-template

PyTorch deep learning projects made easy.

pytorch-transformers

👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)

ravenpack

rcnn

Recurrent & convolutional neural network modules

rubrix

✨ Python framework for data-centric NLP

schemaorg

Schema.org - schemas and (appengine) software

science-parse

Science Parse parses scientific papers (in PDF form) and returns them in structured form.

scrapy

Scrapy, a fast high-level web crawling & scraping framework for Python.

sentence-transformers

Sentence Embeddings with BERT & XLNet

sru

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

sta-663-2017

Notebooks, worksheets and homework for STA 663 class

sta-663-2020

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

tensorflow_install_commands

text

Data loaders and abstractions for text and NLP

theano_tutorial

thready

Single-function module for multi-threading.

torchmoji

A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc

transfer

Code and data for the paper "Multi-Source Domain Adaptation with Mixture of Experts" https://arxiv.org/abs/1809.02256

tskatom.github.io

twitter_finance

ucphrase-exp

This project provides an unsupervised framework for mining and tagging quality phrases on text corpora with pretrained language models (KDD'21).

xtreme

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.