Inspur Suzhou Intelligent Technology Co., Ltd

Lingyan Liang

Yaqian Zhao

Gang Dong

Hongbin Yang

Wenfeng Yin

Haiwei Liu

Qichun Cao

Rengang Li

Dongdong Jiang

A neural network compression method whereby forward inference is performed on target data by using a target parameter sharing network to obtain an output feature map of the last convolutional module, a channel related feature is extracted from the output feature map, the extracted channel related feature and a target constraint condition are input into a target meta-generative network, and an optimal network architecture under the target constraint condition is predicted by using the target meta-generative network to obtain a compressed neural network model.

Neural network compression method, apparatus and device, and storage medium

A system for accelerating an RNN network including: a first cache, which is used for outputting Wto Wor Wto Win parallel in N paths in a cyclic switching manner, and the degree of parallelism is k; a second cache, which is used for outputting xor hin the cyclic switching manner; a vector multiplication circuit, which is used for, by using N groups of multiplication arrays, respectively calculating Wxto Wx, or respectively calculating Whto Wh; an addition circuit, which is used for calculating Wx+Wh+bto Wx+Wh+b; an activation circuit, which is used for performing an activation operation according to an output of the addition circuit; a state updating circuit, which is used for acquiring c, calculating cand h, updating c, and sending hto the second cache; a bias data cache; a vector cache; and a cell state cache.

System and method for accelerating RNN network, and storage medium

A hardware environment-based data quantization method includes: parsing a model file under a current deep learning framework to obtain intermediate computational graph data and weight data that are independent of a hardware environment; performing calculation on image data in an input data set through a process indicated by an intermediate computational graph to obtain feature map data; separately performing uniform quantization on the weight data and the feature map data of each layer according to a preset linear quantization method, and calculating a weight quantization factor and a feature map quantization factor (S); combining the weight quantization factor and the feature map quantization factor to obtain a quantization parameter that makes hardware use shift instead of division; and finally, writing the quantization parameter and the quantized weight data to a bin file according to a hardware requirement so as to generate quantized file data (S).

Hardware environment-based data quantization method and apparatus, and readable storage medium

Growing community of inventors

Jiangsu, China

Lingyan Liang