PyTorch Hub
For Researchers

classify birds using this fine-grained image classifier

DeepLabV3 model with a ResNet-101 backbone

Transformer models for English-French and English-German translation.

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

ResNext models trained with billion scale weakly-supervised data.

A simple generative image model for 64x64 images

High-quality image generation of fashion, celebrity faces

ResNet and ResNext models introduced in the "Billion scale semi-supervised learning for image classification" paper

PyTorch implementations of popular NLP Transformers

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

Single Shot MultiBox Detector model for object detection

The Tacotron 2 model for generating mel spectrograms from text

A Robustly Optimized BERT Pretraining Approach

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.

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

Fully-Convolutional Network model with a ResNet-101 backbone

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

Harmonic DenseNet pre-trained on ImageNet

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

Efficient networks optimized for speed and memory, with residual blocks

Proxylessly specialize CNN architectures for different hardware platforms.

Deep residual networks pre-trained on ImageNet

Next generation ResNets, more efficient and accurate

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

Alexnet-level accuracy with 50x fewer parameters.

Award winning ConvNets from 2014 Imagenet ILSVRC challenge

Wide Residual Networks