Rosun's starred repositories

PaddleHub

Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)

Language:PythonLicense:Apache-2.0Stargazers:12547Issues:184Issues:1292

alphafold

Open source code for AlphaFold.

Language:PythonLicense:Apache-2.0Stargazers:11888Issues:224Issues:824

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Language:PythonLicense:NOASSERTIONStargazers:6828Issues:57Issues:182

pytorch-OpCounter

Count the MACs / FLOPs of your PyTorch model.

Language:PythonLicense:MITStargazers:4710Issues:30Issues:166

OpenPCDet

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Language:PythonLicense:Apache-2.0Stargazers:4369Issues:69Issues:1392

Awesome-Knowledge-Distillation

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

alphafold2

To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released

Language:PythonLicense:MITStargazers:1519Issues:66Issues:48

sparse_attention

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

MaskFormer

Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

Language:PythonLicense:NOASSERTIONStargazers:1295Issues:23Issues:69

PaddleViT

:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

Language:PythonLicense:Apache-2.0Stargazers:1188Issues:10Issues:109

moco-v3

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

Language:PythonLicense:NOASSERTIONStargazers:1157Issues:17Issues:34

Swin-Transformer-Semantic-Segmentation

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

Language:PythonLicense:Apache-2.0Stargazers:1119Issues:12Issues:89

Transformer-in-Computer-Vision

A paper list of some recent Transformer-based CV works.

YOLOS

[NeurIPS 2021] You Only Look at One Sequence

Language:Jupyter NotebookLicense:MITStargazers:810Issues:21Issues:29

PaddleHelix

Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集

Language:PythonLicense:Apache-2.0Stargazers:792Issues:25Issues:80

UniFormer

[ICLR2022] official implementation of UniFormer

Language:PythonLicense:Apache-2.0Stargazers:783Issues:10Issues:128

fair_self_supervision_benchmark

Scaling and Benchmarking Self-Supervised Visual Representation Learning

Language:PythonLicense:NOASSERTIONStargazers:590Issues:22Issues:13
Language:PythonLicense:Apache-2.0Stargazers:351Issues:9Issues:18

ColossalAI-Examples

Examples of training models with hybrid parallelism using ColossalAI

Language:PythonLicense:Apache-2.0Stargazers:333Issues:20Issues:47

PaintTransformer

Official PaddlePaddle implementation of Paint Transformer

Language:PythonLicense:Apache-2.0Stargazers:306Issues:10Issues:12

TorchPQ

Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda

Language:CudaLicense:MITStargazers:203Issues:6Issues:16

FaPN

[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

Language:C++License:Apache-2.0Stargazers:202Issues:6Issues:16

paper-reproduction-tutorials

论文复现技巧与PaddlePaddle优秀复现项目分享

Language:PythonLicense:Apache-2.0Stargazers:129Issues:2Issues:0

ViP

Official implementation of the paper Visual Parser: Representing Part-whole Hierarchies with Transformers

Language:PythonLicense:MITStargazers:124Issues:14Issues:7

TMANet

Official implementation of TMANet.

Language:PythonLicense:Apache-2.0Stargazers:117Issues:3Issues:31

Revisiting-Contrastive-SSL

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [NeurIPS 2021]

Language:PythonLicense:NOASSERTIONStargazers:86Issues:6Issues:2

ProFOLD

A protein 3D structure prediction application

Language:PythonLicense:MITStargazers:63Issues:3Issues:6

PolyphonicFormer

[ECCV 2022] 🎵PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation

MAMP

[ICME 2022] Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation.

Language:PythonLicense:BSD-3-ClauseStargazers:32Issues:1Issues:5

EarlyBERT

[ACL-IJCNLP 2021] "EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets" by Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Zhangyang Wang and Jingjing Liu