Electronic apparatus for compression and decompression of data and compression method thereof
First Claim
1. A data compression method of compressing a weight parameter of an artificial intelligence model, the data compression method comprising:
- pruning, by a processor, an original data comprising a plurality of weight parameters;
identifying, by the processor, at least one first weight parameter of which at least one first value is not changed by the pruning, among multiple weight parameters included in the pruned original data;
obtaining, by the processor, a first index data comprising location information of the at least one first weight parameter of which the at least one first value is not changed;
identifying, by the processor, at least one second weight parameter of which at least one second value is changed by the pruning, among the multiple weight parameters included in the pruned original data;
substituting, by the processor, the at least one second weight parameter of which the at least one second value is changed with a don'"'"'t care parameter,quantizing, by the processor, to a n bit, a first data comprising the at least one first weight parameter of which the at least one first value is not changed and the don'"'"'t care parameter with which the at least one second weight parameter is substituted;
obtaining, by the processor, a n number of second data, based on the first data quantized to the n bit; and
obtaining, by the processor, a n number of compressed data by applying, to a Viterbi algorithm, each of the obtained n number of second data.
1 Assignment
0 Petitions
Accused Products
Abstract
A data compression method and a data decompression method are provided. The method includes pruning an original data including a plurality of weight parameters, identifying at least one first weight parameter of which at least one first value is not changed by the pruning, among multiple weight parameters included in the pruned original data, and obtaining a first index data including location information of the at least one first weight parameter of which the at least one first value is not changed, identifying at least one second weight parameter of which at least one second value is changed by the pruning, among the multiple weight parameters included in the pruned original data, and substituting the at least one second weight parameter of which the at least one second value is changed with a don'"'"'t care parameter.
11 Citations
22 Claims
-
1. A data compression method of compressing a weight parameter of an artificial intelligence model, the data compression method comprising:
-
pruning, by a processor, an original data comprising a plurality of weight parameters; identifying, by the processor, at least one first weight parameter of which at least one first value is not changed by the pruning, among multiple weight parameters included in the pruned original data; obtaining, by the processor, a first index data comprising location information of the at least one first weight parameter of which the at least one first value is not changed; identifying, by the processor, at least one second weight parameter of which at least one second value is changed by the pruning, among the multiple weight parameters included in the pruned original data; substituting, by the processor, the at least one second weight parameter of which the at least one second value is changed with a don'"'"'t care parameter, quantizing, by the processor, to a n bit, a first data comprising the at least one first weight parameter of which the at least one first value is not changed and the don'"'"'t care parameter with which the at least one second weight parameter is substituted; obtaining, by the processor, a n number of second data, based on the first data quantized to the n bit; and obtaining, by the processor, a n number of compressed data by applying, to a Viterbi algorithm, each of the obtained n number of second data. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. An electronic apparatus for compressing a weight parameter of an artificial intelligence model, the apparatus comprising:
-
a memory storing instructions; and a processor configured to execute the stored instructions to; prune an original data comprising a plurality of weight parameters; identify at least one first parameter of which at least one first value is not changed by the pruning, from among multiple weight parameters included in the pruned original data; obtain a first index data comprising location information of the at least one first weight parameter of which the at least one first value is not changed; identify at least one second weight parameter of which at least one second value is changed by the pruning, among the multiple weight parameters included in the pruned original data; substitute the at least one second weight parameter of which the at least one second value is changed with a don'"'"'t care parameter; quantize, to a n bit, a first data comprising the at least one first weight parameter of which the at least one first value is not changed and the don'"'"'t care parameter with which the at least one second weight parameter is substituted; obtain a n number of second data, based on the first data quantized to the n bit; and obtain a n number of compressed data by applying, to a Viterbi algorithm, each of the obtained n number of second data. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
-
17. A decompression method of decompressing a compressed data, the decompression method comprising:
-
receiving, by a processor, a compressed index data and a n number of compressed data; obtaining, by the processor, a first index data by applying the compressed index data to a first Viterbi decompressor; obtaining, by the processor, a n number of first data by applying the n number of compressed data respectively to a plurality of Viterbi decompressors; and obtaining, by the processor, a pruned original data, based on the first index data and the n number of first data. - View Dependent Claims (18)
-
-
19. An electronic apparatus for decompressing a compressed data, the apparatus comprising:
-
a memory storing instructions; and a processor configured to execute the stored instructions to; receive a compressed index data and a n number of compressed data; obtain a first index data by applying the compressed index data to a first Viterbi decompressor; obtain a n number of first data by applying the n number of compressed data respectively to a plurality of Viterbi decompressors; and obtain a pruned original data, based on the first index data and the n number of first data. - View Dependent Claims (20)
-
-
21. A data compression method comprising:
-
pruning, by a processor, an original data comprising a plurality of weight parameters of an artificial intelligence model; obtaining, by the processor, a first index data comprising location information of at least one first weight parameter of which at least one first value is not changed by the pruning, among multiple weight parameters included in the pruned original data; obtaining, by the processor, a first data by; substituting, by the processor, with a don'"'"'t care parameter, at least one second weight parameter of which at least one second value is changed by the pruning, among the multiple weight parameters included in the pruned original data; and quantizing, by the processor, to a n bit, the at least one first weight parameter of which the at least one first value is not changed and the don'"'"'t care parameter with which the at least one second weight parameter is substituted; obtaining, by the processor, a second data, based on the first data quantized to the n bit; and obtaining, by the processor, a compressed index data and a compressed data by applying, to a Viterbi algorithm, each of the first index data and the second data. - View Dependent Claims (22)
-
Specification