Method for super-resolution
AssigneeSamsung Electronics Co., Ltd.
InventorsStylianos I. VENIERIS, Mario ALMEIDA, Royson LEE
Life of this patent
Estimating the term…
Abstract
Broadly speaking, the present techniques generally relate to a computer-implemented method for training a machine learning, ML, model to perform super-resolution on resource-constrained devices.
Claims15
A computer-implemented method for optimising a super-resolution deep neural network of a machine learning, ML, model, for implementation on a processing unit, the method comprising:
- obtaining a pre-trained super-resolution deep neural network, DNN, for performing super-resolution on low resolution images, the DNN comprising a plurality of layers;
- quantising, using scale factors, a wordlength for all values of an activations tensor of each layer of the pre-trained DNN to a uniform wordlength;
- determining, for each layer, whether to keep the uniform wordlength for the values of the activations tensor of the layer or to switch to a new wordlength that is supported by the processing unit;
- and
- quantising a wordlength for all values of the activations tensor of each layer based on the determining, and thereby generating a hybrid-precision DNN optimised for implementation on the processing unit.
The method as claimed in any preceding claim further comprising:
- identifying one or more quantised layers of the DNN to be further quantised at runtime based on a dynamically derived scale factor applied to the activations tensor of the identified quantised layers.
A computer-implemented method for using an optimised super-resolution deep neural network, DNN, of a machine learning, ML, model, on a processing unit to perform super-resolution, the method comprising:
- obtaining at least one low resolution image;
- and
- using the optimised ML model to:
- divide the low resolution image into fixed-size patches to be upscaled;
- upscale a resolution of each fixed-size patch using the optimised ML model, wherein each layer of the optimised ML model has a quantised activations tensor that is either pre-defined or determined using dynamic range estimation at run-time;
- concatenate the upscaled patches to form a super-resolution image;
- and
- output the super-resolution image.
The method for processing input data using AI model including multiple layers in NPU comprising:
- estimating quality drop(PSNR drop) according to lowering bandwidth for each layer;
- determining a layer for quantization among the multiple layers(DRE);
- quantize the determined layer(RQU);
- and
- determining a processing unit of NPU based on the quantization.
Dependencies are inferred from the claim text.