Abstract: Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images using one or more pixel weights determined based, at least in part, on one or more sub-pixel offset values.

Abstract: Apparatuses, systems, and techniques to reduce a size of neural networks. In at least one embodiment, a size of a neural network is reduced by at least removing one or more neurons of the neural network and adjusting one or more layers of the neural network to compensate for the removed one or more neurons.

Abstract: A demasking engine removes masks from a pruned neural network that is represented by a graph of nodes. The demasking engine analyzes a tensor and a mask associated with a given node in the graph of nodes to determine portions of the tensor that are zeroed by the mask. The demasking engine then removes these portions from the tensor to generate a densified tensor that has a smaller dimensionality than the original tensor. A function associated with the node can be evaluated more quickly based on the densified tensor than the original tensor. The demasking engine adds a scatter operation subsequent to the node in order to scale the dimensionality of the densified tensor to the dimensionality associated with the original tensor.