Recognition, reidentification and security enhancements using autonomous machines
A mechanism is described for facilitating recognition, reidentification, and security in machine learning at autonomous machines. A method of embodiments, as described herein, includes facilitating a camera to detect one or more objects within a physical vicinity, the one or more objects including a person, and the physical vicinity including a house, where detecting includes capturing one or more images of one or more portions of a body of the person. The method may further include extracting body features based on the one or more portions of the body, comparing the extracted body features with feature vectors stored at a database, and building a classification model based on the extracted body features over a period of time to facilitate recognition or reidentification of the person independent of facial recognition of the person.
1 . An apparatus comprising:
an autonomous machine including one or more processors including a graphics processor, the graphics processor including a plurality of processing resources, and a memory to store data, including data for neural network processing;
wherein the one or more processors are to:
receive data associated with a first neural network model and a software application,
assign a first set of one or more processing resources of the plurality of processing resources for execution of the first neural network model, and a second set of one or more processing resources of the plurality of processing resources for execution of the software application, wherein assigning the first set of one or more processing resources and the second set of one or more processing resources includes establishing a guard rail including one or more processing resources, the guard rail being located between the first set of one or more processing resources and the second set of one or more processing resources, and
perform separate parallel executions of the first neural network model and the software application utilizing the processing resources of the first set and the second set.
2 . The apparatus of claim 1 , wherein the performance of the parallel executions includes the first neural network model being protected in the first set of one or more processing resources and the software application being isolated from the first neural network model in the second set of one or more processing resources, and wherein there is no overlap between the first set and the second set.
3 . The apparatus of claim 1 , wherein the one or more processing resources of the guard rail are not used for processing during the performance of the separate parallel executions of the first neural network model and the software application.
4 . The apparatus of claim 1 , wherein the guard rail is programmable.
5 . The apparatus of claim 1 , wherein the one or more processors are further to:
receive data associated with a second neural network model;
assign a third set of one or more processing resources of the plurality of processing resources for execution of the second neural network model; and
perform separate parallel executions of the first neural network model, the second neural network model, and the software application utilizing the processing resources of the first set, the second set, and the third set.
6 . The apparatus of claim 1 , wherein the autonomous machine includes an autonomous vehicle, and wherein a decision of the first neural network model includes a decision for operation of the autonomous vehicle.
7 . The apparatus of claim 1 , wherein the graphics processor is co-located with an application processor on a common semiconductor package.
8 . A method comprising:
receiving, at an autonomous machine, data associated with a first neural network model and a software application for the autonomous machine, the autonomous machine including a plurality of processing resources;
assigning, by the autonomous machine, a first set of one or more processing resources of the plurality of processing resources for execution of the first neural network model, and a second set of one or more processing resources of the plurality of processing resources for execution of the software application, wherein assigning the first set of one or more processing resources and the second set of one or more processing resources includes establishing a guard rail including one or more processing resources, the guard rail being located between the first set of one or more processing resources and the second set of one or more processing resources; and
performing, by the autonomous machine, separate parallel executions of the first neural network model and the software application utilizing the processing resources of the first set and the second set.
9 . The method of claim 8 , wherein performing the parallel executions includes the first neural network model being protected in the first set of one or more processing resources and the software application being isolated from the first neural network model in the second set of one or more processing resources, and wherein there is no overlap between the first set and the second set.
10 . The method of claim 8 , wherein the one or more processing resources of the guard rail are not used for processing during the performance of the separate parallel executions of the first neural network model and the software application.
11 . The method of claim 8 , wherein the guard rail is programmable.
12 . The method of claim 8 , further comprising:
receiving, at the autonomous machine, data associated with a second neural network model;
assigning, by the autonomous machine, a third set of one or more processing resources of the plurality of processing resources for execution of the second neural network model; and
performing, by the autonomous machine, separate parallel executions of the first neural network model, the second neural network model, and the software application utilizing the processing resources of the first set, the second set, and the third set.
13 . The method of claim 8 , wherein the autonomous machine includes an autonomous vehicle, and wherein a decision of the first neural network model includes a decision for operation of the autonomous vehicle.
14 . At least one non-transitory machine-readable medium comprising instructions that, when executed by a computing device, cause the computing device to perform operations comprising:
receiving data associated with a first neural network model and a software application for an autonomous machine, the autonomous machine including a plurality of processing resources;
assigning a first set of one or more processing resources of the plurality of processing resources for execution of the first neural network model, and a second set of one or more processing resources of the plurality of processing resources for execution of the software application, wherein assigning the first set of one or more processing resources and the second set of one or more processing resources includes establishing a guard rail including one or more processing resources, the guard rail being located between the first set of one or more processing resources and the second set of one or more processing resources; and
performing separate parallel executions of the first neural network model and the software application utilizing the processing resources of the first set and the second set.
15 . The non-transitory machine-readable medium of claim 14 , wherein performing the parallel executions includes the first neural network model being protected in the first set of one or more processing resources and the software application being isolated from the first neural network model in the second set of one or more processing resources, and wherein there is no overlap between the first set and the second set.
16 . The non-transitory machine-readable medium of claim 14 , wherein the one or more processing resources of the guard rail are not used for processing during the performance of the separate parallel executions of the first neural network model and the software application.
17 . The non-transitory machine-readable medium of claim 14 , wherein the guard rail is programmable.
18 . The non-transitory machine-readable medium of claim 14 , wherein the instructions further include that, when executed by a computing device, cause the computing device to perform operations comprising:
receiving data associated with a second neural network model;
assigning a third set of one or more processing resources of the plurality of processing resources for execution of the second neural network model; and
performing separate parallel executions of the first neural network model, the second neural network model, and the software application utilizing the processing resources of the first set, the second set, and the third set.
19 . The non-transitory machine-readable medium of claim 14 , wherein the autonomous machine includes an autonomous vehicle, and wherein a decision of the first neural network model includes a decision for operation of the autonomous vehicle.