Realtek Semiconductor Inc.

Yu-Che Kao

Ching-Lung Chen

The present invention discloses a neural network construction method having average quantization mechanism that includes steps outlined below. A weight combination included in each of network layers of a neural network is retrieved. A loss function is generated according to the weight combination of all the network layers and target values. Corresponding to each network layers, a Gini coefficient of the weight combination is calculated and the Gini coefficients corresponding to all the network layers are accumulated as a regularized correction term. The loss function and the regularized correction term are merged as a regularized loss function to perform training on the neural network accordingly to generate a trained weight combination of each of the network layers. A quantization is performed on the trained weight combination of each of the network layers to generate a quantized neural network, in which each of the network layers thereof includes the trained weight combination.

Neural network construction method and apparatus having average quantization mechanism

A method and an electronic device for detecting the resolution of a video material are provided. The method is applied to an electronic device, and a calculation circuit of the electronic device executes an AI model. The video material includes multiple frames, and each frame includes multiple sub-frames. The AI model processes multiple pixel data to generate an intermediate resolution corresponding to the pixel data. The method includes the following steps: (A) generating a target sub-frame, the number of pixels of the target sub-frame being smaller than the number of pixels in any frame; (B) inputting the target sub-frame into the AI model to generate the intermediate resolution; (C) storing the intermediate resolution; (D) repeating steps (A) to (C) to generate multiple intermediate resolutions; and (E) determining the resolution of the video material based on the intermediate resolutions.

Growing community of inventors

Hsinchu, Taiwan

Yu-Che Kao