公开(公告)号：US20240251171A1

公开(公告)日：2024-07-25

申请号：US18406006

申请日：2024-01-05

Applicant: NVIDIA CORPORATION

Inventor： Iuri FROSIO ,  Yazhou XING ,  Chao LIU ,  Anjul PATNEY ,  Hongxu YIN ,  Amrita MAZUMDAR ,  Jan KAUTZ

IPC: H04N23/73 ,  H04N23/95

CPC classification number: H04N23/73 ,  H04N23/95

Abstract: One or more embodiments include receiving one or more frames of a live video captured by a video capturing device, wherein the one or more frames include a current frame that is most-recently captured, identifying a set of reference frames included in the one or more frames based on at least the current frame, wherein each frame in the set of reference frames has a different exposure level relative to the current frame, determining, using one or more neural networks, a set of missing details for one or more regions of the current frame based on the set of reference frames, generating an updated version of the current frame based on the set of details, and outputting the updated version of the current frame in real-time.

公开(公告)号：US20240119361A1

公开(公告)日：2024-04-11

申请号：US18348286

申请日：2023-07-06

Applicant: NVIDIA CORPORATION

Inventor： Hongxu YIN ,  Wonmin BYEON ,  Jan KAUTZ ,  Divyam MADAAN ,  Pavlo MOLCHANOV

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: One embodiment of a method for training a first machine learning model having a different architecture than a second machine learning model includes receiving a first data set, performing one or more operations to generate a second data set based on the first data set and the second machine learning model, wherein the second data set includes at least one feature associated with one or more tasks that the second machine learning model was previously trained to perform, and performing one or more operations to train the first machine learning model based on the second data set and the second machine learning model.

公开(公告)号：US20230186077A1

公开(公告)日：2023-06-15

申请号：US17841577

申请日：2022-06-15

Applicant: NVIDIA CORPORATION

Inventor： Hongxu YIN ,  Jan KAUTZ ,  Jose Manuel ALVAREZ LOPEZ ,  Arun MALLYA ,  Pavlo MOLCHANOV ,  Arash VAHDAT

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0481

Abstract: One embodiment of the present invention sets forth a technique for executing a transformer neural network. The technique includes computing a first set of halting scores for a first set of tokens that has been input into a first layer of the transformer neural network. The technique also includes determining that a first halting score included in the first set of halting scores exceeds a threshold value. The technique further includes in response to the first halting score exceeding the threshold value, causing a first token that is included in the first set of tokens and is associated with the first halting score not to be processed by one or more layers within the transformer neural network that are subsequent to the first layer.