Video ResNet

The VideoResNet model is based on the A Closer Look at Spatiotemporal Convolutions for Action Recognition paper.


The video module is in Beta stage, and backward compatibility is not guaranteed.

Model builders

The following model builders can be used to instantiate a VideoResNet model, with or without pre-trained weights. All the model builders internally rely on the base class. Please refer to the source code for more details about this class.

r3d_18(*[, weights, progress])

Construct 18 layer Resnet3D model.

mc3_18(*[, weights, progress])

Construct 18 layer Mixed Convolution network as in

r2plus1d_18(*[, weights, progress])

Construct 18 layer deep R(2+1)D network as in


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources