PaddleScience is SDK and library for developing AI-driven scientific computing applications based on PaddlePaddle.

Deep Learning for humans

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

Codes of the paper: SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks (CVPR2024)

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

Official implementation for NIPS'17 paper: PredRNN: Recurrent Neural Networks for Predictive Learning Using Spatiotemporal LSTMs.

Implementation of TAAConvLSTM and SAAConvLSTM used in "Attention Augmented ConvLSTM for Environment Prediction"

A Hybrid Deep Learning Model with Attention based ConvLSTM Networks for Short-Term Traffic Flow Prediction

Discover the ECMWF Summer of Weather Code 2021 challenges!

Python package to easy access to weather and climate data

[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

post-processing experiments with neural networks

stb single-file public domain libraries for C/C++

a reimplementation of UnFlow in PyTorch that matches the official TensorFlow version

Rethinking Image Inpainting via a Mutual Encoder Decoder with Feature Equalizations. ECCV 2020 Oral

CNNGeometric PyTorch implementation

ncnn is a high-performance neural network inference framework optimized for the mobile platform

StarGAN - Official PyTorch Implementation (CVPR 2018)

Original implementation of the paper "Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation", in ICCV 2019, https://arxiv.org/abs/1908.07433

Learning Symmetry Consistent Deep CNNs for Face Completion

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

Pytorch Re-implementation of "Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting"(CVPR 2020 Oral)

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

A diverse benchmark database for multi-paradigm facial beauty prediction

(CVPR'20 Oral) Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild

A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.

A simple baseline for one-shot multi-object tracking