Optimizing runtime configuration of machine learning models and processing pipelines using data augmentation
AssigneeNVIDIA Corporation
InventorsSwapnil Jagdish Rathi, Bhushan Rupde, Kaustubh Purandare
Life of this patent
Estimating the term…
Abstract
Disclosed are apparatuses, systems, and techniques for implementing automatic runtime selection and tuning of MLM processing pipelines using stream augmentation. In one embodiment, the techniques include augmenting data stream(s) with auxiliary data to obtain an augmented data stream. The techniques further include performing an inference processing of the augmented data stream using a machine learning model (MLM) to obtain a characterization of a presence of the auxiliary data in the augmented data stream and adjusting one or more runtime settings of the MLM using the obtained characterization.
Claims20
A method comprising:
- augmenting, using one or more processing units, one or more data streams with auxiliary data to obtain an augmented data stream;
- performing, using the one or more processing units, an inference processing of the augmented data stream using a machine learning model (MLM) to obtain a characterization of a presence of the auxiliary data in the augmented data stream;
- and
- adjusting, by the one or more processing units, one or more runtime settings of the MLM using the obtained characterization.
A system comprising:
- a processing device to:
- augment one or more data streams with auxiliary data to obtain an augmented data stream;
- perform an inference processing of the augmented data stream using a machine learning model (MLM) to obtain a characterization of a presence of the auxiliary data in the augmented data stream;
- and
- adjust one or more runtime settings of the MLM using the obtained characterization.
A system comprising:
- one or more sensors to generate one or more data streams;
- and
- one or more processing units to:
- augment the one or more data streams with auxiliary data to obtain an augmented data stream;
- perform an inference processing of the augmented data stream using a machine learning model (MLM) to obtain a characterization of a presence of the auxiliary data in the augmented data stream;
- and
- adjust one or more runtime settings of the MLM using the obtained characterization.
Dependencies are inferred from the claim text.