Abstract: A method, a device, and a medium for processing data of a machine learning model are provided. A set of data samples associated with a machine learning model is received. The machine learning model includes a plurality of network blocks, the data of the machine learning model includes first data and second data of a network block of the plurality of network blocks. A data sample of the set of data samples is input to the machine learning model to determine a first full-precision representation of the first data and a second full-precision representation of the second data of the network block respectively. A loss function is determined based on the first full-precision representation, the second full-precision representation, a first compressor having a first compression parameter, and a second compressor having a second compression parameter. Based on the loss function, the first and second compression parameters are updated.

Abstract: Embodiments of the present disclosure relate to a data processing method and apparatus, a device, and a medium.

Abstract: An image super-resolution method includes: performing feature extraction on an image to be subjected to super-resolution, to obtain a first image feature; processing the first image feature through a feature processing module to obtain a second image feature, where the feature processing module includes: a feature refinement unit that includes at least one set of first convolutional layer and first activation function layer that are connected in series and is configured to process an input feature of the feature processing module; a feature fusion unit configured to perform additive fusion on the input feature of the feature processing module and an output feature of the feature refinement unit; and an attention unit configured to process an output feature of the feature fusion unit to obtain an output feature of the feature processing module; and generating, based on the first image feature and the second image feature, a super-resolution image.

Abstract: This application provides a method for generating a high-resolution picture performed by a computer device. The method includes: acquiring at least one deep neural network model; acquiring a low-resolution picture; determining a corresponding deep neural network model according to the low-resolution picture; and converting the low-resolution pictures into a high-resolution picture through the deep neural network model, the deep neural network model including a plurality of non-linear conversion convolution layers that alternately use different parameter matrices as convolution template parameters.

Abstract: This application provides a method for generating a high-resolution picture performed by a computer device. The method includes: acquiring at least one deep neural network model; acquiring a low-resolution picture; determining a corresponding deep neural network model according to the low-resolution picture; and converting the low-resolution pictures into a high-resolution picture through the deep neural network model, the deep neural network model including a plurality of non-linear conversion convolution layers that alternately use different parameter matrices as convolution template parameters.

Abstract: A user runs an album application on a digital device to generate a digital album and share the album with others. The album application creates a message with a first copy of the album and a link to a second copy of the album on a website hosted by a photo sharing provider. The first copy of the album is a small file because it contains low resolution versions of the photos and it uses a compact file format (e.g., Adobe Flash or HTML5). After the message is sent, the album application uploads high resolution versions of the photos to the photo sharing provider. A recipient of the message may view the first copy of the album in the message or click on the link to access the second copy of the album from the website hosted by the photo sharing provider. The recipient may order prints of the album from the photo sharing provider or a print provider working with the photo sharing provider. The recipient may further share the album by forwarding the message or the link to others.