vineyard (v6d): an in-memory immutable data manager. (Project under CNCF, TAG-Storage)

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".

常用文本匹配模型tf版本，数据集为QA_corpus，持续更新中

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。

Chinese GPT2: pre-training and fine-tuning framework for text generation

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型

Tensorflow implementation of attention mechanism for text classification tasks.

🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"

Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

The implementation of text classification using character level convoultion neural networks using Keras

汉字笔画整理，数据来源是一个提供汉字查询的网站

一行代码使用BERT生成句向量，BERT做文本分类、文本相似度计算

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

MovieLens based recommender system.使用MovieLens数据集训练的电影推荐系统。

TensorFlow code and pre-trained models for BERT

知识表示相关学习算法

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

客户借贷回款系统

Example TensorFlow codes and Caicloud TensorFlow as a Service dev environment.