Stars
The Microsoft Office Word template of BUPT Thesis for Master Degree.
Latex template rescuing PhDs in BUPT from dissertations typesetting.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
A latent text-to-image diffusion model
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
Code for paper: Simple and Robust Loss Design for Multi-Label Learning with Missing Labels
Official Implementation of Early-Learning Regularization Prevents Memorization of Noisy Labels
A curated list of resources on continual zero-shot learning
Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
Implementation of the paper Video Action Transformer Network
Transpile trained scikit-learn estimators to C, Java, JavaScript and others.
(CVPR 2021) Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166
A quickstart and benchmark for pytorch distributed training.
Awesome multilingual OCR and Document Parsing toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools,…
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