• 시작하기
  • 블로그
  • 튜토리얼
  • 허브
  • 커뮤니티

PyTorch Hub
For Researchers

Explore and extend models from the latest cutting edge research.

All
Audio
Generative
Nlp
Scriptable
Vision
정렬
  • GitHub Stars
    :: 오름차순
  • GitHub Stars
    :: 내림차순

HybridNets

HybridNets - End2End Perception Network

3D ResNet

Resnet Style Video classification networks pretrained on the Kinetics 400 dataset

SlowFast

SlowFast networks pretrained on the Kinetics 400 dataset

X3D

X3D networks pretrained on the Kinetics 400 dataset

YOLOP

YOLOP pretrained on the BDD100K dataset

MiDaS

MiDaS models for computing relative depth from a single image.

ntsnet

classify birds using this fine-grained image classifier

Open-Unmix

Reference implementation for music source separation

Silero Speech-To-Text Models

A set of compact enterprise-grade pre-trained STT Models for multiple languages.

Silero Text-To-Speech Models

A set of compact enterprise-grade pre-trained TTS Models for multiple languages

Silero Language Classifier

Pre-trained Spoken Language Classifier

Silero Number Detector

Pre-trained Spoken Number Detector

Silero Voice Activity Detector

Pre-trained Voice Activity Detector

YOLOv5

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

Deeplabv3

DeepLabV3 models with ResNet-50, ResNet-101 and MobileNet-V3 backbones

Transformer (NMT)

영어-프랑스어 번역과 영어-독일어 번역을 위한 트랜스포머 모델

ResNext WSL

ResNext models trained with billion scale weakly-supervised data.

DCGAN on FashionGen

64x64 이미지 생성을 위한 기본 이미지 생성 모델

Progressive Growing of GANs (PGAN)

High-quality image generation of fashion, celebrity faces

Semi-supervised and semi-weakly supervised ImageNet Models

Billion scale semi-supervised learning for image classification 에서 제안된 ResNet, ResNext 모델

PyTorch-Transformers

PyTorch implementations of popular NLP Transformers

U-Net for brain MRI

U-Net with batch normalization for biomedical image segmentation with pretrained weights for abnormality segmentation in brain MRI

EfficientNet

EfficientNets are a family of image classification models, which achieve state-of-the-art accuracy, being an order-of-magnitude smaller and faster. Trained with mixed precision using Tensor Cores.

ResNet50

ResNet50 model trained with mixed precision using Tensor Cores.

ResNeXt101

ResNet with bottleneck 3x3 Convolutions substituted by 3x3 Grouped Convolutions, trained with mixed precision using Tensor Cores.

SE-ResNeXt101

ResNeXt with Squeeze-and-Excitation module added, trained with mixed precision using Tensor Cores.

SSD

Single Shot MultiBox Detector model for object detection

Tacotron 2

The Tacotron 2 model for generating mel spectrograms from text

WaveGlow

WaveGlow model for generating speech from mel spectrograms (generated by Tacotron2)

RoBERTa

BERT를 강력하게 최적화하는 사전 학습 접근법, RoBERTa

AlexNet

The 2012 ImageNet winner achieved a top-5 error of 15.3%, more than 10.8 percentage points lower than that of the runner up.

Densenet

Dense Convolutional Network (DenseNet), connects each layer to every other layer in a feed-forward fashion.

FCN

Fully-Convolutional Network model with ResNet-50 and ResNet-101 backbones

GhostNet

Efficient networks by generating more features from cheap operations

GoogLeNet

GoogLeNet was based on a deep convolutional neural network architecture codenamed "Inception" which won ImageNet 2014.

HarDNet

Harmonic DenseNet pre-trained on ImageNet

Inception_v3

Also called GoogleNetv3, a famous ConvNet trained on Imagenet from 2015

MEAL_V2

Boosting Tiny and Efficient Models using Knowledge Distillation.

MobileNet v2

잔차 블록에 기반한 속도와 메모리에 최적화된 효율적인 네트워크

ProxylessNAS

Proxylessly specialize CNN architectures for different hardware platforms.

ResNeSt

A new ResNet variant.

ResNet

Deep residual networks pre-trained on ImageNet

ResNext

Next generation ResNets, more efficient and accurate

ShuffleNet v2

An efficient ConvNet optimized for speed and memory, pre-trained on Imagenet

SqueezeNet

Alexnet-level accuracy with 50x fewer parameters.

vgg-nets

Award winning ConvNets from 2014 Imagenet ILSVRC challenge

Wide ResNet

Wide Residual Networks

PyTorchKorea @ GitHub

파이토치 한국 사용자 모임을 GitHub에서 만나보세요.

GitHub로 이동

한국어 튜토리얼

한국어로 번역 중인 파이토치 튜토리얼을 만나보세요.

튜토리얼로 이동

커뮤니티

다른 사용자들과 의견을 나누고, 도와주세요!

커뮤니티로 이동
  • 파이토치 한국 사용자 모임
  • 사용자 모임 소개
  • 기여해주신 분들
  • 리소스
  • 행동 강령
  • 이 사이트는 독립적인 파이토치 사용자 커뮤니티로, 최신 버전이 아니거나 잘못된 내용이 포함되어 있을 수 있습니다. This site is an independent user community and may be out of date or contain incorrect information.
  • 행동 강령을 읽고 지켜주세요. PyTorch 공식 로고 사용 규정은 Linux Foundation의 정책을 따릅니다. Please read and follow our code of conduct. All PyTorch trademark policy applicable to Linux Foundation's policies.
  • 시작하기
  • 블로그
  • 튜토리얼
  • 허브
  • 커뮤니티