公开(公告)号：US20210350210A1

公开(公告)日：2021-11-11

申请号：US17041336

申请日：2018-07-30

Applicant: INTEL CORPORATION

Inventor： Jiong GONG ,  Haihao SHEN ,  Xiao Dong LIN ,  Xiaoli LIU

IPC: G06N3/04 ,  G06F7/483 ,  G06F17/16 ,  G06N3/08 ,  G06N3/063

Abstract: A method and apparatus for keeping statistical inference accuracy with 8-bit winograd convolution. A calibration dataset and a pretrained CNN comprising 32-bit floating point weight values may be sampled to generate an input activation tensor and a weight tensor. A transformed input activation tensor may be generated by multiplying the input activation tensor and an input matrix to generate a transformed input activation tensor. A transformed weight tensor may be generated by multiplying the weight tensor and a weight matrix. A scale factor may be computed for each transformed tensor. An 8-bit CNN model including the scale factors may be generated.

公开(公告)号：US20180173614A1

公开(公告)日：2018-06-21

申请号：US15576491

申请日：2015-06-26

Applicant: INTEL CORPORATION

Inventor： Jiong GONG ,  Yun WANG ,  Haihao SHEN

IPC: G06F11/36

CPC classification number: G06F11/3664 ,  G06F3/0304 ,  G06F3/0481 ,  G06F3/04817 ,  G06F11/3688

Abstract: Technologies for device-independent application testing include a host computing device and one or more test computing devices. The host computer device records user interface events generated by an application of the test computing device and video data indicative of the display interface of the application. The host computing device detects user interface objects in the video data that correspond to user interface events using a computer vision algorithm, which may include image feature detection or optical character recognition. The host computing device generates an object-based test script that identifies the user interface object and a user interaction. The host computing device may identify the user interface object in the display interface of an application executed by a different test computing device using the computer vision algorithm. The host computing device performs the specified user interaction on the detected user interface object. Other embodiments are described and claimed.

公开(公告)号：US20250045586A1

公开(公告)日：2025-02-06

申请号：US18717275

申请日：2022-03-04

Applicant: Intel Corporation

Inventor： Hengyu MENG ,  Jiong GONG ,  Xudong LIU ,  Haihao SHEN

IPC: G06N3/082

Abstract: The application provides a method and apparatus for accelerating deep learning inference based on a HW-aware sparsity pattern. The method may include determining a hardware-aware sparsity pattern based on a register width specified by an ISA of a hardware unit for implementing the DNN for deep learning inference, the sparsity pattern specifying a block size and a sparsity ratio for block-wise sparsification of a weight matrix of an operator in the DNN; performing the block-wise sparsification for the weight matrix based on the sparsity pattern to obtain a sparse weight matrix, during a training process of the DNN; compressing the sparse weight matrix into a concentrated weight matrix by removing all-zero blocks from the sparse weight matrix; and generating a mask to indicate an index of each row of non-zero blocks in the sparse weight matrix to enable extraction of corresponding elements from an activation matrix of the operator.

公开(公告)号：US20250077861A1

公开(公告)日：2025-03-06

申请号：US18574995

申请日：2021-11-03

Applicant: Intel Corporation

Inventor： Haihao SHEN ,  Feng TIAN ,  Xi CHEN ,  Huma ABIDI ,  Yuwen ZHOU

IPC: G06N3/08 ,  G06N3/0495 ,  G06V10/774

Abstract: The disclosure provides an apparatus, method, device and medium for label-balanced calibration in post-training quantization of DNNs. An apparatus includes interface circuitry configured to receive a training dataset and processor circuitry coupled to the interface circuitry. The processor circuitry is configured to generate a small ground truth dataset by selecting images with a ground truth number of 1 from the training dataset; generate a calibration dataset randomly from the training dataset; if any image in the calibration dataset has the ground truth number of 1, remove the image from the small ground truth dataset; generate a label balanced calibration dataset by replacing an image with a ground truth number greater than a preset threshold in the calibration dataset with a replacing image selected randomly from the small ground truth dataset; and perform calibration using the label balanced calibration dataset in post-training quantization. Other embodiments are disclosed and claimed.

公开(公告)号：US20240289612A1

公开(公告)日：2024-08-29

申请号：US18571150

申请日：2021-10-26

Applicant: Intel Corporation

Inventor： Haihao SHEN ,  Hengyu MENG ,  Feng TIAN

IPC: G06N3/08 ,  G06N5/04

CPC classification number: G06N3/08 ,  G06N5/04

Abstract: The application provides a hardware-aware cost model for optimizing inference of a deep neural network (DNN) comprising: a computation cost estimator configured to compute estimated computation cost based on input tensor, weight tensor and output tensor from the DNN; and a memory/cache cost estimator configured to perform memory/cache cost estimation strategy based on hardware specifications, wherein the hardware-aware cost model is used to perform performance simulation on target hardware to provide dynamic quantization knobs to quantization as required for converting a conventional precision inference model to an optimized inference model based on the result of the performance simulation.