bobo199830

stable-diffusion

A latent text-to-image diffusion model

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

ShameCom

收集校招污点公司或组织，帮助学弟学妹避雷。互联网不曾遗忘！

pytorch-distributed

A quickstart and benchmark for pytorch distributed training.

PytorchOCR

基于Pytorch的OCR工具库，支持常用的文字检测和识别算法

sklearn-porter

Transpile trained scikit-learn estimators to C, Java, JavaScript and others.

Event-Extraction

近年来事件抽取方法总结，包括中文事件抽取、开放域事件抽取、事件数据生成、跨语言事件抽取、小样本事件抽取、零样本事件抽取等类型，DMCNN、FramNet、DLRNN、DBRNN、GCN、DAG-GRU、JMEE、PLMEE等方法

TimeSformer-pytorch

Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification

BUPTGraduateThesis

ELR

Official Implementation of Early-Learning Regularization Prevents Memorization of Noisy Labels

FSOD-code

BUPTMasterThesisWord

The Microsoft Office Word template of BUPT Thesis for Master Degree.

RePRI-for-Few-Shot-Segmentation

(CVPR 2021) Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166

Video-Action-Transformer-Network-Pytorch-

Implementation of the paper Video Action Transformer Network

robust-loss-mlml

Code for paper: Simple and Robust Loss Design for Multi-Label Learning with Missing Labels

bupTemplate

Latex template rescuing PhDs in BUPT from dissertations typesetting.

diffusion

awesome-continual-zero-shot-learning

A curated list of resources on continual zero-shot learning