Back to results
US 2024/0403635 A1Published application
Method for adaptive distribution of cnns on heterogeneous devices using parallelization
AssigneeInterDigital CE Patent Holdings, SAS
InventorsAnne LAMBERT, Alexey OZEROV, Patrick FONTAINE
Life of this patent
Estimating the term…
Abstract
A method or apparatus that combines properties of parallel distribution and flexibility of distribution of convolutional neural networks on heterogeneous devices uses parallelization for distributed inference of Deep Neural Networks. The method addresses parallel distribution among various numbers of devices of various capacities. A network is distributed in parallel for each configuration and is adaptive to different network capabilities.
Claims12
A method, comprising:
- determining availability and capabilities of at least one device in a convolutional neural network;
- determining whether a modification is available in the at least one device or in capabilities of the at least one device, and if a modification is available, determining and sending an updated or convolutional neural network configuration;
- sending an input image of parallel sub-networks to the at least one device;
- executing sub-networks to process the input image in the at least one device according to a received configuration;
- and,
- receiving output by the at least one device to a controller to execute fusion of a processed image.
3 more elements
An apparatus, comprising:
- a processor, configured to perform:
- determining availability and capabilities of at least one device in a convolutional neural network;
- determining whether a modification is available in the at least one device or in capabilities of the at least one device, and if a modification is available, determining and sending an updated convolutional neural network configuration;
- sending an input image of parallel sub-networks to the at least one device;
- executing sub-networks to process the input image in the at least one device according to a received configuration;
- and,
- receiving output by the at least one device to a controller to execute fusion of a processed image.
4 more elements
The method of claim, implemented for video encoding.
(canceled)
Dependencies are inferred from the claim text.