Method and device for reducing a size of a neural network model

1. A method for reducing a size of a neural network model, comprising:

compressing data of the neural network model;

identifying structure information of a vector register, wherein the structure information includes a number of registers included in the vector register;

comparing a number of elements in the compressed data of the neural network model with a first condition, wherein the first condition is determined based on the number of registers in the vector register;

in response to the number of elements satisfying the first condition, associating the compressed data of the neural network model with the vector register to enable loading the compressed data of the neural network model to the vector register;

in response to the number of elements satisfying the first condition, sending an indication to end compression of the data;

comparing the number of elements in the compressed data of the neural network model with a second condition, wherein the second condition is determined based on the number of registers in the vector register, and is different from the first condition; and

adjusting a structure of the vector register in response to the number of elements satisfying the second condition,

wherein satisfying the first condition comprises being equal to or smaller than the number of registers in the vector register, and wherein satisfying the second condition comprises being equal to or smaller than one half of the number of registers in the vector register.

2. The method of claim 1 , wherein compressing the data of the neural network model comprises pruning of the data.

3. The method of claim 1 , wherein the data is a weight matrix of the neural network model.

4. The method of claim 1 , wherein adjusting the structure of the vector register comprises:

reducing the number of registers in the vector register by one half.

5. The method of claim 1 , wherein compressing the data of the neural network model comprises a first operation of compression, the method further comprising:

performing a second operation of compression of the data in response to the number of elements not satisfying the first condition.

6. The method of claim 1 , further comprising:

generating an instruction set based on the association between the compressed data and the vector register to load the compressed data to the vector register.

7. The method of claim 1 , wherein the vector register is part of a group of vector registers that include elements that are executed simultaneously.

8. An apparatus for reducing a size of a neural network model, comprising:

a memory storing a set of instructions; and

one or more processors configured to execute the set of instruction to cause the apparatus to perform:

compressing data of the neural network model,

identifying structure information of a vector register, wherein the structure information includes a number of registers included in the vector register,

comparing a number of elements in the compressed data of the neural network model with a first condition, wherein the first condition is determined based on the number of registers in the vector register,

in response to the number of elements satisfying the first condition, associating the compressed data of the neural network model with the vector register to enable loading the compressed data of the neural network model to the vector register,

in response to the number of elements satisfying the first condition, sending an indication to end compression of the data,

comparing the number of elements in the compressed data of the neural network model with a second condition, wherein the second condition is determined based on the number of registers in the vector register, and is different from the first condition; and

adjusting a structure of the vector register in response to the number of elements satisfying the second condition,

wherein satisfying the first condition comprises being equal to or smaller than the number of registers in the vector register, and wherein satisfying the second condition comprises being equal to or smaller than one half of the number of registers in the vector register.

9. A non-transitory computer readable medium that stores a set of instructions that is executable by at least one processor of a computer to cause the computer to perform a method for reducing a size of a neural network model, the method comprising:

compressing data of the neural network model;

identifying structure information of a vector register, wherein the structure information includes a number of registers included in the vector register;

comparing a number of elements in the compressed data of the neural network model with a first condition, wherein the first condition is determined based on the number of registers in the vector register;

in response to the number of elements satisfying the first condition, associating the compressed data of the neural network model with the vector register to enable loading the compressed data of the neural network model to the vector register;

in response to the number of elements satisfying the first condition, sending an indication to end compression of the data;

comparing the number of elements in the compressed data of the neural network model with a second condition, wherein the second condition is determined based on the number of registers in the vector register, and is different from the first condition; and

adjusting a structure of the vector register in response to the number of elements satisfying the second condition,

wherein satisfying the first condition comprises being equal to or smaller than the number of registers in the vector register, and wherein satisfying the second condition comprises being equal to or smaller than one half of the number of registers in the vector register.

10. The non-transitory computer readable medium of claim 9 , wherein compressing the data of the neural network model comprises pruning of the data.

11. The non-transitory computer readable medium of claim 9 , wherein the data is the weight matrix of a neural network model.

12. The non-transitory computer readable medium of claim 9 , wherein adjusting the structure of the vector register comprises:

reducing the number of registers in the vector register by one half.

13. The non-transitory computer readable medium of claim 9 , wherein compressing the data of the neural network model comprises a first operation of compression, the method further comprising:

performing a second operation of compression of the data in response to the number of elements not satisfying the first condition.

14. The non-transitory computer readable medium of claim 9 , wherein the set of instructions that are executable by the at least one processor of a computer to cause the computer to further perform:

generating an instruction set based on the association between the compressed data and the vector register to load the compressed data to the vector register.