fanfanba Goto Github PK

tencent2017_final_coda_allegro

腾讯2017社交广告源码（决赛排名第23位）

tencent2019_preliminary_rank1st

The code for 2019 Tencent College Algorithm Contest, and the online result ranks 1st in the preliminary.

tencent_social_ads

第一届腾讯社交广告高校算法大赛(全国14名)

text-classsification-using-knowledge-distillation-from-google-bert-classifier

Toxic Comment Classification on Wikipedia Comments dataset.

textclassify

基于预训练模型的文本分类模板，CCF BDCI新闻情感分析初赛A榜4/2735，复赛1%

textmatch

基于Pytorch的，中文语义相似度匹配模型（ABCNN、Albert、Bert、BIMPM、DecomposableAttention、DistilBert、ESIM、RE2、Roberta、SiaGRU、XlNet）

tf-multitask-pos-ner

Deep multi-task learning for POS-tagging and NER using tensorflow.

tf-seq2seq

(nmt参考)Sequence to sequence learning using TensorFlow.

topical_word_embeddings

A demo code for topical word embedding

transfer

Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks

transformer

A TensorFlow Implementation of the Transformer: Attention Is All You Need

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

uer-py

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

unisound_asr

unisound_asr 云知声 python版接口

unsupervised-vocabulary-search

完整的新词发现&词库构建例子

vae

a simple vae and cvae from keras

vector_similarity

Python, Java implementation of TS-SS called from "A Hybrid Geometric Approach for Measuring Similarity Level Among Documents and Document Clustering"

vitis_libraries

Vitis Libraries

vslam

vslam

webdataproduct

A Web Page Of Public Sentiment For P2P Industry( P2P 行业的舆情分析前端展示)

webqa-using-dgcnn

pytorch-Reimplementation of DGCNN

wechatmagician

WechatMagician is a Xposed module written in Kotlin, that can prevent Wechat from recalling messages, deleting moments or comments.

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

wenzheng

ai challenger 2018细粒度情感分类第一名解决方案, A training framework itegrating tensorflow and pytorch

xiaomei

a small, simple and beautiful web framework.

xuan-bike

yake

Single-document unsupervised keyword extraction

zhihu

seq2seq 1.4 知乎专栏源码

zhihu-text-classification

[2017知乎看山杯 多标签 文本分类] ye组(第六名) 解题方案

zqcnn

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求），800星公布更准的106点模型