Abstract: The disclosure relates to method and system for on-device inference in a deep neural network (DNN). The method comprises: determining whether one or more layers of the DNN satisfy one of a first, a second and a third condition, the one or more layers including one or more convolution layers and one or more resampling layers; performing the on-device inference based on the determination, wherein performing the on-device inference comprises at least one of: optimizing the one or more convolution layers in the one or more parallel branches based on the one or more layers of the DNN satisfying the first condition, optimizing the at least one of the resampling layers based on the one or more layers of the DNN satisfying the second condition, and modifying operation of the at least one of the resampling layers based on the one or more layers of the DNN satisfying the third condition.

Abstract: Accordingly embodiments herein disclose a method for predicting optimal number of thread for an application in an electronic device. The method includes receiving, by an application thread controller, a request to predict a number of threads to be spawned from the application in real-time. Further, the method includes measuring, by the application thread controller, a current state of the electronic device based on the request received from the application. Further, the method includes predicting, by the application thread controller, the optimal number of threads to be spawned for the application based on a scheduler-behaviour model and the current state of the electronic device. Further, the method includes recommending, by the application thread controller, the number of threads to be spawned by the application based on the prediction.

Abstract: Accordingly embodiments herein disclose a method for predicting optimal number of thread for an application in an electronic device. The method includes receiving, by an application thread controller, a request to predict a number of threads to be spawned from the application in real-time. Further, the method includes measuring, by the application thread controller, a current state of the electronic device based on the request received from the application. Further, the method includes predicting, by the application thread controller, the optimal number of threads to be spawned for the application based on a scheduler-behaviour model and the current state of the electronic device. Further, the method includes recommending, by the application thread controller, the number of threads to be spawned by the application based on the prediction.