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.
Ultralytics YOLOv5 🚀 for object detection, instance segmentation and image classification.
56.8k
A Robustly Optimized BERT Pretraining Approach
32.2k
Award winning ConvNets from 2014 ImageNet ILSVRC challenge
17.5k
An efficient ConvNet optimized for speed and memory, pre-trained on ImageNet
17.5k
Next generation ResNets, more efficient and accurate
17.5k
Deep residual networks pre-trained on ImageNet
17.5k
Efficient networks optimized for speed and memory, with residual blocks
17.5k
Also called GoogleNetv3, a famous ConvNet trained on ImageNet from 2015
17.5k
GoogLeNet was based on a deep convolutional neural network architecture codenamed “Inception” which won ImageNet 2014.
17.5k
Fully-Convolutional Network model with ResNet-50 and ResNet-101 backbones
17.5k
Dense Convolutional Network (DenseNet), connects each layer to every other layer in a feed-forward fashion.
17.5k
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.
17.5k
DeepLabV3 models with ResNet-50, ResNet-101 and MobileNet-V3 backbones
17.5k
WaveGlow model for generating speech from mel spectrograms (generated by Tacotron2)
14.7k
The Tacotron 2 model for generating mel spectrograms from text
14.7k
Single Shot MultiBox Detector model for object detection
14.7k
ResNeXt with Squeeze-and-Excitation module added, trained with mixed precision using Tensor Cores.
14.7k
ResNet with bottleneck 3×3 Convolutions substituted by 3×3 Grouped Convolutions, trained with mixed precision using Tensor Cores.
14.7k
ResNet50 model trained with mixed precision using Tensor Cores.
14.7k
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.
14.7k
The HiFi GAN model for generating waveforms from mel spectrograms
14.7k
GPUNet is a new family of Convolutional Neural Networks designed to max out the performance of NVIDIA GPU and TensorRT.
14.7k
MiDaS models for computing relative depth from a single image.
5.3k
Brain-inspired Multilayer Perceptron with Spiking Neurons
4.4k
Efficient networks by generating more features from cheap operations
4.4k
X3D networks pretrained on the Kinetics 400 dataset
3.5k
SlowFast networks pretrained on the Kinetics 400 dataset
3.5k
Resnet Style Video classification networks pretrained on the Kinetics 400 dataset
3.5k
YOLOP pretrained on the BDD100K dataset
2.2k
Once-for-all (OFA) decouples training and search, and achieves efficient inference across various edge devices and resource constraints.
1.9k
Proxylessly specialize CNN architectures for different hardware platforms.
1.4k
Networks with domain/appearance invariance
808
U-Net with batch normalization for biomedical image segmentation with pretrained weights for abnormality segmentation in brain MRI
769
Boosting Tiny and Efficient Models using Knowledge Distillation.
701
ResNext models trained with billion scale weakly-supervised data.
603
Harmonic DenseNet pre-trained on ImageNet
370
Lets Keep it simple, Using simple architectures to outperform deeper and more complex architectures
53
classify birds using this fine-grained image classifier
34
