公开(公告)号：US20240412035A1

公开(公告)日：2024-12-12

申请号：US18500014

申请日：2023-11-01

Applicant: QUALCOMM Incorporated

Inventor： Anuj GUPTA ,  Himanshu UPRETI ,  Venkata Subba Dheeraj GATTUPALLI ,  Vinayak Narayan BADDI ,  Prasanna Ashish BISWAS ,  Mohit SHARMA ,  Anusha V.S BHAMIDIPATI ,  Piyush SHARMA

IPC: G06N3/042

Abstract: A processor-implemented method of pre-processing for deep neural network compilation comprising receiving a representation of an artificial neural network (ANN) model. The ANN includes multiple nodes coupled by edges. Position information is determined for each node of the ANN. An operator embedding is generated to represent operators of the ANN model in an embedding space based on the position information. A graph neural network (GNN) processes the operator embedding to generate a graph embedding corresponding to the ANN model according to a learned distance metric and based on the position information. The GNN determines a set of hyperparameters for the ANN model based on the graph embedding.

公开(公告)号：US20150063694A1

公开(公告)日：2015-03-05

申请号：US14254770

申请日：2014-04-16

Applicant: QUALCOMM Incorporated

Inventor： Nitesh SHROFF ,  Ramin REZAIIFAR ,  Piyush SHARMA ,  William Edward MANTZEL

IPC: G06T11/60

CPC classification number: G06T11/60

Abstract: Techniques are described for combining two or more images that are taken with varying brightness degrees to generate a composite image. In one embodiment, at least two weight masks are generated based on one or more characteristics of the two or more images. A first image A first weight mask is used to combine color channels of one or more pixels of the two or more images and a second weight mask is used to combine intensity channels of the one or more pixels of the two or more images.

Abstract translation: 描述用于组合以不同亮度度拍摄的两个或更多个图像以产生合成图像的技术。 在一个实施例中，基于两个或多个图像的一个或多个特征产生至少两个权重掩模。 第一图像第一加权蒙版用于组合两个或多个图像中的一个或多个像素的颜色通道，并且第二加权蒙版用于组合两个或多个图像中的一个或多个像素的强度通道。