PLSCPaddle Large Scale Classification Tools,supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, DeiT, FaceViT.
Stars: ✭ 113 (-15.67%)
mmselfsupOpenMMLab Self-Supervised Learning Toolbox and Benchmark
Stars: ✭ 2,315 (+1627.61%)
LaTeX-OCRpix2tex: Using a ViT to convert images of equations into LaTeX code.
Stars: ✭ 1,566 (+1068.66%)
pytorch-vitAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Stars: ✭ 250 (+86.57%)
mobilevit-pytorchA PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer".
Stars: ✭ 349 (+160.45%)
libaiLiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training
Stars: ✭ 284 (+111.94%)
Revisiting-Contrastive-SSLRevisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [NeurIPS 2021]
Stars: ✭ 81 (-39.55%)
SimclrSimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
Stars: ✭ 2,720 (+1929.85%)
HugsVisionHugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
Stars: ✭ 154 (+14.93%)
SimSiamExploring Simple Siamese Representation Learning
Stars: ✭ 52 (-61.19%)
SimMIMThis is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".
Stars: ✭ 717 (+435.07%)
SReTOfficial PyTorch implementation of our ECCV 2022 paper "Sliced Recursive Transformer"
Stars: ✭ 51 (-61.94%)
towheeTowhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Stars: ✭ 821 (+512.69%)
MSFOfficial code for "Mean Shift for Self-Supervised Learning"
Stars: ✭ 42 (-68.66%)
OrientedRepPoints DOTAOriented Object Detection: Oriented RepPoints + Swin Transformer/ReResNet
Stars: ✭ 62 (-53.73%)
BossNAS(ICCV 2021) BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search
Stars: ✭ 125 (-6.72%)
simsiam-cifar10Code to train the SimSiam model on cifar10 using PyTorch
Stars: ✭ 33 (-75.37%)
MiniVoxCode for our ACML and INTERSPEECH papers: "Speaker Diarization as a Fully Online Bandit Learning Problem in MiniVox".
Stars: ✭ 15 (-88.81%)
YOLOSYou Only Look at One Sequence (NeurIPS 2021)
Stars: ✭ 612 (+356.72%)
GCLList of Publications in Graph Contrastive Learning
Stars: ✭ 25 (-81.34%)
G-SimCLRThis is the code base for paper "G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling" by Souradip Chakraborty, Aritra Roy Gosthipaty and Sayak Paul.
Stars: ✭ 69 (-48.51%)
photo-magician🎨 provide some common image process apis with canvas
Stars: ✭ 12 (-91.04%)
CVPR21 PASSPyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"
Stars: ✭ 55 (-58.96%)
FKDA Fast Knowledge Distillation Framework for Visual Recognition
Stars: ✭ 49 (-63.43%)
clip-containerA containerized REST API around OpenAI's CLIP model.
Stars: ✭ 46 (-65.67%)
SimCLR-in-TensorFlow-2(Minimally) implements SimCLR (https://arxiv.org/abs/2002.05709) in TensorFlow 2.
Stars: ✭ 75 (-44.03%)
PySODEvalToolkitPySODEvalToolkit: A Python-based Evaluation Toolbox for Salient Object Detection and Camouflaged Object Detection
Stars: ✭ 59 (-55.97%)
video repres mascode for CVPR-2019 paper: Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
Stars: ✭ 63 (-52.99%)
newtNatural World Tasks
Stars: ✭ 24 (-82.09%)
GCA[WWW 2021] Source code for "Graph Contrastive Learning with Adaptive Augmentation"
Stars: ✭ 69 (-48.51%)
SoCo[NeurIPS 2021 Spotlight] Aligning Pretraining for Detection via Object-Level Contrastive Learning
Stars: ✭ 125 (-6.72%)
visualizationa collection of visualization function
Stars: ✭ 189 (+41.04%)
BYOLBootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Stars: ✭ 102 (-23.88%)
pillar-motionSelf-Supervised Pillar Motion Learning for Autonomous Driving (CVPR 2021)
Stars: ✭ 98 (-26.87%)
sc depth plPytorch Lightning Implementation of SC-Depth (V1, V2...) for Unsupervised Monocular Depth Estimation.
Stars: ✭ 86 (-35.82%)
esvitEsViT: Efficient self-supervised Vision Transformers
Stars: ✭ 323 (+141.04%)
SelfTask-GNNImplementation of paper "Self-supervised Learning on Graphs:Deep Insights and New Directions"
Stars: ✭ 78 (-41.79%)
MoTISMobile(iOS) Text-to-Image search powered by multimodal semantic representation models(e.g., OpenAI's CLIP). Accepted at NAACL 2022.
Stars: ✭ 60 (-55.22%)
SimCLRPytorch implementation of "A Simple Framework for Contrastive Learning of Visual Representations"
Stars: ✭ 65 (-51.49%)
koclipKoCLIP: Korean port of OpenAI CLIP, in Flax
Stars: ✭ 80 (-40.3%)
InterpretDLInterpretDL: Interpretation of Deep Learning Models,基于『飞桨』的模型可解释性算法库。
Stars: ✭ 121 (-9.7%)
Transformers-TutorialsThis repository contains demos I made with the Transformers library by HuggingFace.
Stars: ✭ 2,828 (+2010.45%)
info-nce-pytorchPyTorch implementation of the InfoNCE loss for self-supervised learning.
Stars: ✭ 160 (+19.4%)
Swin-Transformer-Semantic-SegmentationThis is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.
Stars: ✭ 856 (+538.81%)
Evo-ViTOfficial implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
Stars: ✭ 50 (-62.69%)
AdCoAdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
Stars: ✭ 148 (+10.45%)
SelfSupervisedLearning-DSMcode for AAAI21 paper "Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion“
Stars: ✭ 26 (-80.6%)
Paddle-SEQ低代码序列数据处理框架,最短两行即可完成训练任务!
Stars: ✭ 13 (-90.3%)
GeDMLGeneralized Deep Metric Learning.
Stars: ✭ 30 (-77.61%)
Paddle-Adversarial-ToolboxPaddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.
Stars: ✭ 16 (-88.06%)