xbmu Goto Github PK

algorithms

Minimal examples of data structures and algorithms in Python

amsgrad-tensorflow

Simple Tensorflow implementation of AMSGrad Optimizer (ICLR 2018)

bert-pytorch

Google AI 2018 BERT pytorch implementation

botok

🏷 བོད་ཏོག [pʰøtɔk̚] Tibetan word tokenizer in Python

branchless-utf8

Branchless UTF-8 decoder

chinese-names-corpus

中文人名语料库。中文姓名,姓氏,名字,称呼,日本人名,翻译人名,英文人名。

chinese-poetry

最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

crosswall

:heart: 翻墙小工具，适合学术粉使用

ctoy

Interactive C coding environment

deeplearning

Python for “Deep Learning”，《深度学习》(花书) 数学推导、原理剖析与源码级别代码实现

dgk_lost_conv

dgk_lost_conv 中文对白语料 chinese conversation corpus

foolnltk

A Chinese Nature Language Toolkit

hat-trie

C++ implementation of a fast and memory efficient HAT-trie

hopfield-layers

Hopfield Networks is All You Need

length-adaptive-transformer

linear-attention-transformer

Transformer based on a variant of attention that is linear complexity in respect to sequence length

linear-multihead-attention

Reproducing the Linear Multihead Attention introduced in Linformer paper (Linformer: Self-Attention with Linear Complexity)

linformer-pytorch

My take on a practical implementation of Linformer for Pytorch. https://arxiv.org/pdf/2006.04768.pdf

lrp_for_lstm

minlp

XiaoMi Natural Language Processing Toolkits

nematus

neural-machine-translation-tools

Neural Machine Translation (NMT) Tools - a collection of tools for alignment extraction from NMT attention-based alignment matrices and smarter processing of unknown words in factored models.

pdf2htmlex

Convert PDF to HTML without losing text or format.

python-small-examples

告别枯燥，60 秒学会一个 Python 小例子

pytorch-original-transformer

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

reuzel

A tiny C++ thread pool

rnnsharp

RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above versions. RNNSharp supports many different types of networks, such as forward and bi-directional network, sequence-to-sequence network, and different types of layers, such as LSTM, Softmax, sampled Softmax and others.

simple-and-effective-paraphrastic-similarity

Python code for training models in the ACL paper, "Simple and Effective Paraphrastic Similarity from Parallel Translations".

sparse-map

C++ implementation of a memory efficient hash map and hash set

structured

code for Learning Structured Text Representations