PyTorch HubFor Researchers – PyTorch (original) (raw)

Explore and extend models from the latest cutting edge research.

Discover and publish models to a pre-trained model repository designed for research exploration. Check out the models for Researchers, or learn How It Works. Contribute Models.

*This is a beta release – we will be collecting feedback and improving the PyTorch Hub over the coming months.

YOLOv5

Ultralytics YOLOv5 🚀 for object detection, instance segmentation and image classification.

54.4k

RoBERTa

A Robustly Optimized BERT Pretraining Approach

31.6k

ResNet

Deep residual networks pre-trained on ImageNet

17.0k

ResNext

Next generation ResNets, more efficient and accurate

17.0k

ShuffleNet v2

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

17.0k

Deeplabv3

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

17.0k

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.

17.0k

Densenet

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

17.0k

vgg-nets

Award winning ConvNets from 2014 ImageNet ILSVRC challenge

17.0k

FCN

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

17.0k

GoogLeNet

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

17.0k

Inception_v3

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

17.0k

MobileNet v2

Efficient networks optimized for speed and memory, with residual blocks

17.0k

SSD

Single Shot MultiBox Detector model for object detection

14.4k

Tacotron 2

The Tacotron 2 model for generating mel spectrograms from text

14.4k

WaveGlow

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

14.4k

GPUNet

GPUNet is a new family of Convolutional Neural Networks designed to max out the performance of NVIDIA GPU and TensorRT.

14.4k

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.

14.4k

HiFi GAN

The HiFi GAN model for generating waveforms from mel spectrograms

14.4k

ResNet50

ResNet50 model trained with mixed precision using Tensor Cores.

14.4k

ResNeXt101

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

14.4k

SE-ResNeXt101

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

14.4k

MiDaS

MiDaS models for computing relative depth from a single image.

5.0k

SNNMLP

Brain-inspired Multilayer Perceptron with Spiking Neurons

4.3k

GhostNet

Efficient networks by generating more features from cheap operations

4.3k

3D ResNet

Resnet Style Video classification networks pretrained on the Kinetics 400 dataset

3.5k

SlowFast

SlowFast networks pretrained on the Kinetics 400 dataset

3.5k

X3D

X3D networks pretrained on the Kinetics 400 dataset

3.5k

YOLOP

YOLOP pretrained on the BDD100K dataset

2.0k

Once-for-All

Once-for-all (OFA) decouples training and search, and achieves efficient inference across various edge devices and resource constraints.

1.9k

ProxylessNAS

Proxylessly specialize CNN architectures for different hardware platforms.

1.4k

IBN-Net

Networks with domain/appearance invariance

805

U-Net for brain MRI

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

754

MEAL_V2

Boosting Tiny and Efficient Models using Knowledge Distillation.

696

ResNext WSL

ResNext models trained with billion scale weakly-supervised data.

602

HarDNet

Harmonic DenseNet pre-trained on ImageNet

369

SimpleNet

Lets Keep it simple, Using simple architectures to outperform deeper and more complex architectures

53

ntsnet

classify birds using this fine-grained image classifier

35