GraNet 기반의 필터 프루닝을 적용한 경량 모델의 양자화 효과에 대한 연구A Study of Quantization Effect on a Lightweight Model with GraNet Filter Pruning
- Other Titles
- A Study of Quantization Effect on a Lightweight Model with GraNet Filter Pruning
- Authors
- 설광수; 노시동; 정기석
- Issue Date
- Nov-2022
- Publisher
- 대한임베디드공학회
- Keywords
- Deep learning; Model compresion; Pruning; Quantization
- Citation
- 2022 대한임베디드공학회 추계학술대회, v.0, no.0, pp.296 - 299
- Indexed
- OTHER
- Journal Title
- 2022 대한임베디드공학회 추계학술대회
- Volume
- 0
- Number
- 0
- Start Page
- 296
- End Page
- 299
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/188562
- Abstract
- As convolutional neural networks get deeper and wider, model compression is being widely used to reduce the amount of computation and memory usage. Pruning, which includes structured pruning and unstructured pruning, is one of the widely-adopted model compression methods. The structured pruning can reduce the size of the network model by model thinning, but it may suffer from worse accuracy degradation than the unstructured method. In this study, we claim that if quantization is used in conjunction with the structured pruning, the data size can be reduced without significantly sacrificing the model's performance. We propose a lightweight model on which both the GraNet structured pruning and an 8-bit weight quantization are applied. We evaluate the performance of both static and dynamic quantization to quantize the pruned model. The experiment was conducted to perform image classification tasks using the ResNet18 model with pruning and quantization on CIFAR-100 datasets. Compared to the original model, we reduced the weight size of the model by 84.25%, 88%, and 96.25% with constraints of 2.5%, 5%, and 10% accuracy degradation using GraNet filter pruning and 8-bit quantization.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/188562)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.