Method and apparatus with neural network parameter quantization

1. A processor-implemented method, the method comprising:

determining a first quantization value by performing log quantization on a parameter from one of input activation values and weight values in a layer of a neural network;

comparing a threshold value with an error between a first dequantization value obtained by dequantization of the first quantization value and the parameter;

determining a second quantization value by performing log quantization on the error in response to the error being greater than the threshold value as a result of the comparing; and

quantizing the parameter to a value in which the first quantization value and the second quantization value are grouped.

2. The method of claim 1 ,

wherein the determining of the first quantization value comprises:

determining the first quantization value by performing log quantization on a value corresponding to a quantization level closest to the parameter, from among a plurality of quantization levels, and

the determining of the second quantization value comprises:

determining the second quantization value by performing log quantization on a value corresponding to a quantization level closest to the error, from among the plurality of quantization levels.

3. The method of claim 1 , wherein the second quantization value is represented by a same number of bits as a number of bits representing the first quantization value.

4. The method of claim 1 , wherein the threshold value is determined based on a predetermined trade-off relationship between a recognition rate of the neural network and a size of data according to the quantization of the parameter.

5. The method of claim 1 , wherein the quantizing comprises:

adding a tag bit to each of the first quantization value and the second quantization value.

6. The method of claim 5 , wherein the adding comprises:

adding a first tag bit, indicating that there is the second quantization value subsequent to the first quantization value, before a first bit of bits representing the first quantization value or after a last bit of the bits, and

adding a second tag bit, indicating that there is no quantization value subsequent to the second quantization value, before a first bit of bits representing the second quantization value or after a last bit of the bits.

7. The method of claim 1 , wherein the quantizing comprises:

adding a code value, indicating that the first quantization value and the second quantization value are consecutive values, before a first bit of bits representing the first quantization value or after a last bit of bits representing the second quantization value.

8. The method of claim 1 , further comprising:

dequantizing the value in which the first quantization value and the second quantization value are grouped; and

performing a convolution operation between a dequantization value obtained by dequantizing the value and the input activation values.

9. The method of claim 8 , wherein the dequantizing of the value comprises:

calculating each of a first dequantization value, which is a value obtained by dequantization of the first quantization value, and a second dequantization value, which is a value obtained by dequantization of the second quantization value; and

obtaining the dequantization value by adding the first dequantization value and the second dequantization value.

10. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1 .

11. An apparatus, the apparatus comprising:

one or more processors configured to:

determine a first quantization value by performing log quantization on a parameter from one of input activation values and weight values in a layer of a neural network;

compare a threshold value with an error between a first dequantization value obtained by dequantization of the first quantization value and the parameter;

determine a second quantization value by performing log quantization on the error in response to the error being greater than the threshold value as a result of the comparing; and

quantize the parameter to a value in which the first quantization value and the second quantization value are grouped.

12. The apparatus of claim 11 , wherein the one or more processors are further configured to:

determine the first quantization value by performing log quantization on a value corresponding to a quantization level closest to the parameter, from among a plurality of quantization levels; and

determine the second quantization value by performing log quantization on a value corresponding to a quantization level closest to the error, from among the plurality of quantization levels.

13. The apparatus of claim 11 , wherein the second quantization value is represented by a same number of bits as a number of bits representing the first quantization value.

14. The apparatus of claim 11 , wherein the threshold value is determined based on a predetermined trade-off relationship between a recognition rate of the neural network and a size of data according to the quantization of the parameter.

15. The apparatus of claim 11 , wherein the one or more processors are further configured to add a tag bit to each of the first quantization value and the second quantization value.

16. The apparatus of claim 15 , wherein the one or more processors are further configured to:

add a first tag bit, indicating that there is the second quantization value subsequent to the first quantization value, before a first bit of bits representing the first quantization value or after a last bit of the bits; and

add a second tag bit, indicating that there is no quantization value subsequent to the second quantization value, before a first bit of bits representing the second quantization value or after a last bit of the bits.

17. The apparatus of claim 11 , wherein the one or more processors are further configured to add a code value, indicating that the first quantization value and the second quantization value are consecutive values, before a first bit of bits representing the first quantization value or after a last bit of bits representing the second quantization value.

18. The apparatus of claim 11 , wherein the one or more processors are further configured to:

dequantize the value in which the first quantization value and the second quantization value are grouped; and

perform a convolution operation between a dequantization value obtained by dequantizing the value and the input activation values.

19. The apparatus of claim 18 , wherein the one or more processors are further configured to:

calculate each of a first dequantization value, which is a value obtained by dequantization of the first quantization value, and a second dequantization value, which is a value obtained by dequantization of the second quantization value; and

obtain the dequantization value by adding the first dequantization value and the second dequantization value.