# US 12,602,749 B2 · Parameter optimizing method of neural network and computing apparatus > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,602,749 B2 - Document ID: US12602749B2 - Status: Granted - Kind: B2 - Application number: 18/408,601 - Filed: 2024-01-10 - Published: 2024-09-05 - Granted: 2026-04-14 - Earliest claimed: 2023-03-05 - Assignees: Genesys Logic, Inc. - Applicants: Genesys Logic, Inc. - Inventors: Chuan-Yue Yang - Web page: https://patentgrep.com/patent/US12602749B2 ## CPC - G06T 5/60: using machine learning, e.g. neural networks - G06T 2207/20016: Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A parameter optimizing method of a neural network and a computing apparatus are provided. A shared filter is obtained, and the shared filter includes multiple shared weights. Those shared weights are assigned to multiple sub-filters. Each sub-filter corresponds to one of multiple channels. Each sub-filter includes multiple sub-weights. The size of each sub-filter is smaller than or equal to the size of the shared filter. The sub-weights of each sub-filter are generated according to the assigned shared weight. The sub-filters of those channels are used to be computed with one or more pieces of input data respectively. Thereby, checkerboard artifacts may be reduced or avoided. ## Claims ### Claim 1 A parameter optimizing method of a neural network, comprising: obtaining a shared filter, wherein the shared filter comprises a plurality of shared weights; assigning the shared weights to a plurality of sub-filters, wherein each of the sub-filters corresponds to one of a plurality of channels, each of the sub-filters comprises a plurality of sub-weights, and a size of each of the sub-filters is smaller than or equal to a size of the shared filter; generating the sub-weights of each of the sub-filters according to assigned shared weights; and performing a computation with at least one input data by using the sub-filters of the channels respectively. ### Claim 2 (depends on 1) The parameter optimizing method of a neural network according to claim 1, wherein assigning the shared weights to the sub-filters comprises: defining a plurality of areas of the shared filter according to the size of each of the sub-filters, wherein a number of the sub-weights in each of the sub-filters is the same as a number of the areas, a plurality of shared weights located in one area have the same value, and the shared weights in each of the areas have different values; mapping the sub-filters to the shared filter to generate a mapping result, wherein the mapping result comprises the area of the shared filter to which each of the sub-weights of each of the sub-filters corresponds; and assigning the shared weights according to the mapping result, wherein each selected sub-weight of a corresponding selected area of each of the sub-filters corresponds to at least one of the shared weights in the area mapped. ### Claim 3 (depends on 2) The parameter optimizing method of a neural network according to claim 2, wherein generating the sub-weights of each of the sub-filters according to the assigned shared weights comprises: for each of the sub-filters, obtaining the sub-weights by adding up the corresponding shared weights in the area of the shared filter to which each selected sub-weight in each selected area is mapped. ### Claim 4 (depends on 2) The parameter optimizing method of a neural network according to claim 2, wherein the sub-filters comprise a first sub-filter and a second sub-filter, and mapping the sub-filters to the shared filter comprises: setting at least one of the shared weights of the shared filter mapped to a selected area of the first sub-filter to be different from at least one of the shared weights of the shared filter mapped to a selected area of the second sub-filter. ### Claim 5 (depends on 1) The parameter optimizing method of a neural network according to claim 1, wherein the computation is a first convolution operation, the at least one input data comprises a plurality of pieces of first input data corresponding to the channels, and performing the computation with the at least one input data by using the sub-filters of the channels respectively comprises: performing the first convolution operation on one of the sub-filters and one piece of the first input data respectively according to the corresponding channel to generate a plurality of pieces of first output data corresponding to the channels; and performing a first format conversion on the first output data to generate second output data of a single channel. ### Claim 6 (depends on 5) The parameter optimizing method of a neural network according to claim 5, wherein the number of the channels is N, and performing the first format conversion on the first output data comprises: assigning first elements at the same position in the pieces of first output data to N adjacent elements in the second output data. ### Claim 7 (depends on 5) The parameter optimizing method of a neural network according to claim 5, wherein before performing the first convolution operation on one of the sub-filters and one piece of the first input data respectively according to the corresponding channel, the parameter optimizing method further comprises: performing a second format conversion on a first image to generate the first input data corresponding to the channels. ### Claim 8 (depends on 5) The parameter optimizing method of a neural network according to claim 5, wherein before performing the first convolution operation on one of the sub-filters and one piece of the first input data respectively according to the corresponding channel, the parameter optimizing method further comprises: performing a first encoding on a second image to generate the first input data corresponding to the channels, wherein the first encoding comprises an average pooling or a second format conversion for conversion from a single channel to multiple channels. ### Claim 9 (depends on 5) The parameter optimizing method of a neural network according to claim 5, wherein before performing the first convolution operation on one of the sub-filters and one piece of the first input data respectively according to the corresponding channel, the parameter optimizing method further comprises: performing at least a second convolution operation on a third image to generate the first input data corresponding to the channels. ### Claim 10 (depends on 1) The parameter optimizing method of a neural network according to claim 1, wherein the computation is a first convolution operation, the at least one input data comprises second input data of a single channel, and performing the computation with the at least one input data by using the sub-filters of the channels respectively comprises: performing the first convolution operation on the sub-filters and the second input data respectively to generate a plurality of pieces of third output data corresponding to the channels; and performing a first format conversion on the third output data to generate fourth output data of a single channel. ### Claim 11 (depends on 1) The parameter optimizing method of a neural network according to claim 1, wherein after performing the computation with the at least one input data by using the sub-filters of the channels respectively, the parameter optimizing method further comprises: generating output data, wherein the input data has a first resolution, the output data has a second resolution, and the second resolution is higher than the first resolution, and the size of the shared filter is the same as a size of the output data. ### Claim 12 A computing apparatus, comprising: a storage configured to store a program code; and a processor coupled to the storage and configured to load and execute the program code to: obtain a shared filter, wherein the shared filter comprises a plurality of shared weights; assign the shared weights to a plurality of sub-filters, wherein each of the sub-filters corresponds to one of a plurality of channels, each of the sub-filters comprises a plurality of sub-weights, and a size of each of the sub-filters is smaller than or equal to a size of the shared filter; generate the sub-weights of each of the sub-filters according to the assigned shared weights; and perform a computation with at least one input data by using the sub-filters of the channels respectively. ### Claim 13 (depends on 12) The computing apparatus according to claim 12, wherein the processor is further configured to: define a plurality of areas of the shared filter according to the size of each of the sub-filters, wherein a number of the sub-weights in each of the sub-filters is the same as a number of the areas, a plurality of shared weights located in one area have the same value, and the shared weights in each of the areas have different values; map the sub-filters to the shared filter to generate a mapping result, wherein the mapping result comprises the area of the shared filter to which each of the sub-weights of each of the sub-filters corresponds; and assign the shared weights according to the mapping result, wherein each selected sub-weight of a corresponding selected area of each of the sub-filters corresponds to at least one of the shared weights in the area mapped. ### Claim 14 (depends on 13) The computing apparatus according to claim 13, wherein the processor is further configured to: for each of the sub-filters, obtain the sub-weights by adding up the corresponding shared weights in the area of the shared filter to which each selected sub-weight in each selected area is mapped. ### Claim 15 (depends on 13) The computing apparatus according to claim 13, wherein the sub-filters comprise a first sub-filter and a second sub-filter, and the processor is further configured to: set at least one of the shared weights of the shared filter mapped to a selected area of the first sub-filter to be different from at least one of the shared weights of the shared filter mapped to a selected area of the second sub-filter. ### Claim 16 (depends on 12) The computing apparatus according to claim 12, wherein the computation is a first convolution operation, the at least one input data comprises a plurality of pieces of first input data corresponding to the channels, and the processor is further configured to: perform the first convolution operation on one of the sub-filters and one piece of the first input data respectively according to the corresponding channel to generate a plurality of pieces of first output data corresponding to the channels; and perform a first format conversion on the first output data to generate second output data of a single channel. ### Claim 17 (depends on 16) The computing apparatus according to claim 16, wherein the number of the channels is N, and the processor is further configured to: assign first elements at the same position in the pieces of first output data to N adjacent elements in the second output data. ### Claim 18 (depends on 16) The computing apparatus according to claim 16, wherein the processor is further configured to: perform a second format conversion on a first image to generate the first input data corresponding to the channels. ### Claim 19 (depends on 16) The computing apparatus according to claim 16, wherein the processor is further configured to: perform a first encoding on a second image to generate the first input data corresponding to the channels, wherein the first encoding comprises an average pooling or a second format conversion for conversion from a single channel to multiple channels. ### Claim 20 (depends on 16) The computing apparatus according to claim 16, wherein the processor is further configured to: perform at least a second convolution operation on a third image to generate the first input data corresponding to the channels. ### Claim 21 (depends on 12) The computing apparatus according to claim 12, wherein the computation is a first convolution operation, the at least one input data comprises second input data of a single channel, and the processor is further configured to: perform the first convolution operation on the sub-filters and the second input data respectively to generate a plurality of pieces of third output data corresponding to the channels; and perform a first format conversion on the third output data to generate fourth output data of a single channel. ### Claim 22 (depends on 12) The computing apparatus according to claim 12, wherein the processor is further configured to: generate output data, wherein the input data has a first resolution, the output data has a second resolution, and the second resolution is higher than the first resolution, and the size of the shared filter is the same as a size of the output data.