Single Shot MultiBox Detector model for object detection

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

ResNet with bottleneck 3x3 Convolutions substituted by 3x3 Grouped Convolutions, trained with mixed precision using…

ResNet50 model trained with mixed precision using Tensor Cores.

EfficientNets are a family of image classification models, which achieve state-of-the-art accuracy, being an order-of-magnitude…

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

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

ResNext models trained with billion scale weakly-supervised data.

GPUNet is a new family of Convolutional Neural Networks designed to max out the performance…

classify birds using this fine-grained image classifier

MiDaS models for computing relative depth from a single image.

YOLOP pretrained on the BDD100K dataset

X3D networks pretrained on the Kinetics 400 dataset

SlowFast networks pretrained on the Kinetics 400 dataset

Resnet Style Video classification networks pretrained on the Kinetics 400 dataset