Making large AI models cheaper, faster and more accessible

A high-performance distributed training framework for Reinforcement Learning

[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

飞桨大模型开发套件，提供大语言模型、跨模态大模型、生物计算大模型等领域的全流程开发工具链。

LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training

Paddle Large Scale Classification Tools，supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, Swin, DeiT, CaiT, FaceViT, MoCo, MAE, ConvMAE, CAE.

[CVPR 2021] SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

Globally Applicable Framework for Integrated Hydrological-Hydrodynamic Modelling (GLOFRIM)

DSIR large-scale data selection framework for language model training

NeuroEvolution Optimization with Reinforcement Learning

[MICCAI'23] Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train

A package designed for efficient face recognition across extensive photo collections, optimized for large-scale processing.

Read, write and update large scale pandas DataFrame with Elasticsearch

An efficient 3D semantic segmentation framework for Urban-scale point clouds like SensatUrban, Campus3D, etc.

Welcome to D-BAS! This is a prototype of our dialog-based argumentation system.

MFBN: Multilevel framework for bipartite networks

Python implementation of RLS-Nystrom

We present a set of all-reduce compatible gradient compression algorithms which significantly reduce the communication overhead while maintaining the performance of vanilla SGD. We empirically evaluate the performance of the compression methods by training deep neural networks on the CIFAR10 dataset.

[DEPRECEATED] Multi-Instrumental Music Transformer trained on 12GB/400k MIDIs