Neural network model compression with structured weight unification
AssigneeTencent America LLC
InventorsWei JIANG, Wei WANG, Shan LIU
Life of this patent
Estimating the term…
Abstract
A method, computer program, and computer system is provided for compressing a neural network model. One or more indices corresponding to a multi-dimensional tensor associated with a neural network are reordered. A set of weight coefficients associated with the one or more reordered indices is unified. A model of the neural network is compressed based on the unified set of weight coefficients.
Claims20
A method for compressing a neural network model, executable by a processor, comprising:
- reordering one or more indices corresponding to a multi-dimensional tensor associated with a neural network;
- unifying a set of weight coefficients associated with the one or more reordered indices;
- and
- compressing a model of the neural network based on the unified set of weight coefficients.
A computer system for compressing a neural network model, the computer system comprising:
- one or more computer-readable non-transitory storage media configured to store computer program code;
- and
- one or more computer processors configured to access said computer program code and operate as instructed by said computer program code, said computer program code including:
- reordering code configured to cause the one or more computer processors to reorder one or more indices corresponding to a multi-dimensional tensor associated with a neural network;
- unifying code configured to cause the one or more computer processors to unify a set of weight coefficients associated with the one or more reordered indices;
- and
- compressing code configured to cause the one or more computer processors to compress a model of the neural network based on the unified set of weight coefficients.
A non-transitory computer readable medium having stored thereon a computer program for compressing a neural network model, the computer program configured to cause one or more computer processors to:
- reorder one or more indices corresponding to a multi-dimensional tensor associated with a neural network;
- unify a set of weight coefficients associated with the one or more reordered indices;
- and
- compress a model of the neural network based on the unified set of weight coefficients.
Dependencies are inferred from the claim text.