🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

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…

TensorFlow code and pre-trained models for BERT

deep learning for image processing including classification and object-detection etc.

ALiPy: Active Learning in Python is an active learning python toolbox, which allows users to conveniently evaluate, compare and analyze the performance of active learning methods.

Official code for VisProg (CVPR 2023 Best Paper!)

Multi-Modal learning toolkit based on PaddlePaddle and PyTorch, supporting multiple applications such as multi-modal classification, cross-modal retrieval and image caption.

Official implementation of "CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding" (CVPR, 2022)

A pure python implementation of ML-KEM (FIPS 203) and CRYSTALS-Kyber

Code for our paper "Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation"

Pytorch Implementation of "Sinkhorn Distance Minimization for Knowledge Distillation", COLING 2024 and TNNLS 2024

MixGen: A New Multi-Modal Data Augmentation

[AAAI 2023] COSMOS: Catching Out-of-Context Misinformation using Self Supervised Learning

细粒度图像分类之十二猫分类，对比ResNet和ViT两者模型性能。

FaKnow is designed for reproducing and developing fake news detection algorithms.