公开(公告)号：US20210374554A1

公开(公告)日：2021-12-02

申请号：US17402114

申请日：2021-08-13

Applicant: Intel Corporation

Inventor： Chandrakant Khandelwal ,  Ritesh Kumar Rajore ,  Laxmi Ganesan ,  Sai Jayanthi ,  Yamini Nimmagadda

IPC: G06N3/10 ,  G06F8/41 ,  G06F16/901

Abstract: Systems, apparatuses and methods may provide for technology that parses, at runtime, a deep learning graph in topological order to identify a plurality of nodes, marks a first set of nodes in the plurality of nodes as unsupported by target hardware, and marks a second set of nodes in the plurality of nodes as supported by the target hardware, wherein the first set of nodes and the second set of nodes are marked based on one or more attributes defining operation functionality, and wherein the one or more attributes include one or more of an input node parameter, a dimension, or a shape.

公开(公告)号：US12242973B2

公开(公告)日：2025-03-04

申请号：US17402114

申请日：2021-08-13

Applicant: Intel Corporation

Inventor： Chandrakant Khandelwal ,  Ritesh Kumar Rajore ,  Laxmi Ganesan ,  Sai Jayanthi ,  Yamini Nimmagadda

IPC: G06N3/10 ,  G06F8/41 ,  G06F9/445 ,  G06F16/901

Abstract: Systems, apparatuses and methods may provide for technology that parses, at runtime, a deep learning graph in topological order to identify a plurality of nodes, marks a first set of nodes in the plurality of nodes as unsupported by target hardware, and marks a second set of nodes in the plurality of nodes as supported by the target hardware, wherein the first set of nodes and the second set of nodes are marked based on one or more attributes defining operation functionality, and wherein the one or more attributes include one or more of an input node parameter, a dimension, or a shape.

公开(公告)号：US20240346801A1

公开(公告)日：2024-10-17

申请号：US18750388

申请日：2024-06-21

Applicant: Intel Corporation

Inventor： Priyanka Mudgal ,  Rita Hanna Wouhaybi ,  Caleb Mark McMillan ,  Patrick L. Connor ,  Ritesh Kumar Rajore ,  Jennifer Marie Williams

IPC: G06V10/44

CPC classification number: G06V10/44 ,  G06V2201/07

Abstract: Example apparatus disclosed herein are to generate first descriptive data of a first physical characteristic of a first object based on first camera sensor data from a first camera sensor, and generate second descriptive data of a second physical characteristic of a second object based on second camera sensor data from a second camera sensor different from the first camera sensor. Disclosed example apparatus are also identify, based on the first descriptive data and the second descriptive data, common physical characteristics associated with both the first object and the second object, first unique physical characteristics associated with the first object, and second unique physical characteristics associated with the second object. Disclosed example apparatus are further to identify the first object and the second object as one of a same object or different objects based on the common physical characteristics, the first unique physical characteristics, and the second unique physical characteristics.