公开(公告)号：US20250036715A1

公开(公告)日：2025-01-30

申请号：US18715083

申请日：2021-12-03

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Saki HATTA ,  Hiroyuki UZAWA ,  Shuhei YOSHIDA ,  Yuko IINUMA ,  Yuya OMORI ,  Daisuke KOBAYASHI ,  Ken NAKAMURA

IPC: G06F17/15

Abstract: There is provided a data processing device 10 that performs a convolution operation of two pieces of input data of 2M×N bits (N is a positive integer and M is a natural number) width with a minimum accuracy of the convolution operation being N bits, and performs processing corresponding to a plurality of the consecutive M, the data processing device 10 including: a product-sum operation unit 101 that performs a product-sum operation according to the value of M; a shifter 102 that performs shift processing on a result of a product-sum operation of the product-sum operation unit 101 in a case where the value of M is not 0; an addition unit 103 that performs addition processing on each output of the shifter 102 or the product-sum operation unit 101 according to the value of M; a selector 105 that selects an output from the addition unit 103 according to the value of M; a cumulative addition unit 106 that cumulatively adds the outputs from the selector 105; and a cumulative addition memory 107 that stores outputs from the cumulative addition unit 106 in a process of a convolution operation.

公开(公告)号：US20240289593A1

公开(公告)日：2024-08-29

申请号：US18572329

申请日：2021-06-25

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Shuhei YOSHIDA ,  Hiroyuki UZAWA ,  Daisuke KOBAYASHI ,  Ken NAKAMURA ,  Saki HATTA ,  Yuya OMORI

IPC: G06N3/0464

CPC classification number: G06N3/0464

Abstract: A first aspect of the present disclosure is a convolutional neural network inference processing device that performs processing in a convolutional neural network including a plurality of convolution layers and a residual layer that adds intermediate data related to the plurality of convolution layers as an addition target to a processing result by the plurality of convolution layers for each tile that is data obtained by dividing input data into a predetermined size, the convolutional neural network inference processing device including an inconsistency data storage unit that stores inconsistency data that is data at a portion where there is inconsistency between the processing result and the intermediate data, a past layer data storage unit that stores past layer data that is an addition target in a residual layer generated using inconsistency data related to the tile for which processing has been performed in a past and the intermediate data, and a processing unit that performs processing by the plurality of convolution layers and processing by the residual layer that adds the past layer data to the processing result.

公开(公告)号：US20240232593A9

公开(公告)日：2024-07-11

申请号：US18269528

申请日：2020-12-28

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Saki HATTA ,  Hiroyuki UZAWA ,  Shuhei YOSHIDA ,  Daisuke KOBAYASHI ,  Yuya OMORI ,  Ken NAKAMURA ,  Koyo NITTA

IPC: G06N3/063

CPC classification number: G06N3/063

Abstract: In a data processing device, a fixed-point position control unit determines, as first control. The fixed-point position control unit causes a detection calculation unit to perform calculation processing on processing target data at a processing point in time. The saturation rate control unit instructs, as second control to be repeated by the fixed-point position control unit, the fixed-point position control unit to move at least the fixed-point position as control to increase a lower limit saturation rate proportional to a magnitude of a counted lower limit counter value with respect to a result of the first control. The fixed-point position control unit performs, as the second control, a predetermined determination on the basis of the instruction from the saturation rate control unit and the metadata, determines the fixed-point position moved for each layer, and causes calculation processing to be performed.

公开(公告)号：US20240135155A1

公开(公告)日：2024-04-25

申请号：US18269528

申请日：2020-12-28

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Saki HATTA ,  Hiroyuki UZAWA ,  Shuhei YOSHIDA ,  Daisuke KOBAYASHI ,  Yuya OMORI ,  Ken NAKAMURA ,  Koyo NITTA

IPC: G06N3/063

CPC classification number: G06N3/063

Abstract: In a data processing device, a fixed-point position control unit determines, as first control. The fixed-point position control unit causes a detection calculation unit to perform calculation processing on processing target data at a processing point in time. The saturation rate control unit instructs, as second control to be repeated by the fixed-point position control unit, the fixed-point position control unit to move at least the fixed-point position as control to increase a lower limit saturation rate proportional to a magnitude of a counted lower limit counter value with respect to a result of the first control. The fixed-point position control unit performs, as the second control, a predetermined determination on the basis of the instruction from the saturation rate control unit and the metadata, determines the fixed-point position moved for each layer, and causes calculation processing to be performed.

公开(公告)号：US20240054181A1

公开(公告)日：2024-02-15

申请号：US18256005

申请日：2020-12-09

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Yuya OMORI ,  Ken NAKAMURA ,  Daisuke KOBAYASHI ,  Koyo NITTA

IPC: G06F17/16 ,  G06F7/50

CPC classification number: G06F17/16 ,  G06F7/50

Abstract: One aspect of the present invention is an operation circuit for performing a convolution operation of input feature map information supplied as a plurality of channels and coefficient information supplied as a plurality of channels, the operation circuit including a set including at least two channels of an output feature map based on output channels and at least three sub-operation circuits, wherein at least two sub-operation circuits are allocated for each set, the sub-operation circuits included in the set execute processing of a convolution operation of the coefficient information and the input feature map information included in the set, when a specific channel of the output feature map is a zero matrix, a sub-operation circuit that performs a convolution operation of the zero matrix executes processing of a convolution operation of the coefficient information and the input feature map information to be supplied next from a channel of the output feature map and a channel of the input feature map included in the set, and a result of the convolution operation is output for each channel of the output feature map.

公开(公告)号：US20240273874A1

公开(公告)日：2024-08-15

申请号：US18567353

申请日：2021-12-08

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Ken NAKAMURA ,  Yuya OMORI ,  Daisuke KOBAYASHI ,  Shuhei YOSHIDA ,  Saki HATTA ,  Hiroyuki UZAWA ,  Koyo NITTA

IPC: G06V10/77 ,  G06V10/82

CPC classification number: G06V10/7715 ,  G06V10/82

Abstract: When an output feature map to be an output of convolution processing is output, the output feature map is output to a storage unit for each of divided small regions. When each small region is output to the storage unit, in a case where a feature included in the small region is the same as a predetermined feature or a feature of a small region output in the past, the predetermined feature or the feature of a small region output in the past is compressed and output to the storage unit.

公开(公告)号：US20230409914A1

公开(公告)日：2023-12-21

申请号：US18037645

申请日：2020-11-30

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Shuhei YOSHIDA ,  Hiroyuki UZAWA ,  Saki HATTA ,  Yuya OMORI ,  Daisuke KOBAYASHI ,  Ken NAKAMURA ,  Koyo NITTA

IPC: G06N3/082 ,  G06N3/0464

CPC classification number: G06N3/082 ,  G06N3/0464 ,  G06V10/82

Abstract: The integration unit 26, using configuration information of the convolutional neural network model and each filter used in each convolutional layer of the convolutional neural network model as inputs, deletes one or more pieces of activation function processing performed between the plurality of convolutional layers and integrates a plurality of filters used in the plurality of convolutional layers.

公开(公告)号：US20230053579A1

公开(公告)日：2023-02-23

申请号：US17796528

申请日：2020-02-25

Applicant: Nippon Telegraph and Telephone Corporation

Inventor： Yuya OMORI ,  Ken NAKAMURA ,  Daisuke KOBAYASHI ,  Hiroe IWASAKI

IPC: H04N19/137 ,  H04N19/96 ,  H04N19/176

Abstract: A coding method is a coding method executed by a coding apparatus. The coding method includes partitioning a first block having a predetermined size in an original image into a group of second blocks each being a block serving as a unit for coding, by quad tree, ternary tree, or binary tree, and predicting movement for each of the second blocks. The partitioning includes first sub-partitioning and second sub-partitioning, the first sub-partitioning includes partitioning the first block into blocks each having a size selected from sizes determined according to the quad tree, the ternary tree, or the binary tree, and the second sub-partitioning includes further partitioning the blocks each having the selected size to generate the second blocks.

公开(公告)号：US20230022215A1

公开(公告)日：2023-01-26

申请号：US17783056

申请日：2019-12-09

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Yuya OMORI ,  Ken NAKAMURA ,  Daisuke KOBAYASHI ,  Hiroe IWASAKI

IPC: H04N19/119 ,  H04N19/176 ,  H04N19/182 ,  H04N19/14

Abstract: A coding method encodes an image by dividing the image into blocks, and comprises: dividing a coding target image into a plurality of coding unit blocks; determining whether or not to encode by dividing the coding unit block into a plurality of sub-coding unit blocks, on a basis of an edge direction and an edge strength of an edge obtained for each pixel in the coding unit block; and encoding, in a case of determining to divide the coding unit block into a plurality of sub-coding unit blocks in the determining step, a first sub-coding unit block by referencing a second sub-coding unit block inside the same coding unit block as the first sub-coding unit block.

公开(公告)号：US20240370694A1

公开(公告)日：2024-11-07

申请号：US18561276

申请日：2021-05-26

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Saki HATTA ,  Hiroyuki UZAWA ,  Shuhei YOSHIDA ,  Daisuke KOBAYASHI ,  Yuya OMORI ,  Ken NAKAMURA ,  Koyo NITTA

IPC: G06N3/04

Abstract: An object detection device subjects fixed-length data having a decimal point position set therein to an arithmetic processing corresponding to respective layers in a plurality of layers configuring a multilayer neural network to which an input image is input, the arithmetic processing being performed in accordance with a processing algorithm for the multilayer neural network to which an input image is input. In the arithmetic processing, the object detection device counts the upper limit number of saturations, which is a number of times that upper limit value of a value range determined by the decimal point position is exceeded, and the lower limit number of saturations, which is a number of times that the lower limit value of the value range is not reached. The object detection device counts the upper limit number of saturation layers, which is a number of layers in which the upper limit number of saturations is one or larger, and the lower limit number of saturation layers, which is a number of layers in which the lower limit number of saturations is one or larger. The object detection device changes at least one of the upper limit saturation threshold, which is the threshold of the upper limit number of saturations or the lower limit saturation threshold, which is the threshold of the lower limit number of saturations, when at least one of the upper limit saturation threshold or the lower limit saturation threshold is determined not to be optimal based on an amount of change in the upper limit number of saturation layers and an amount of change in the lower limit number of saturation layers. The object detection device sets the decimal point position for each layer in the plurality of layers, based on a result of the determination.