A Novel Deep Learning Model Compression Algorithm

In order to solve the problem of large model computing power consumption, this paper proposes a novel model compression algorithm. Firstly, this paper proposes an interpretable weight allocation method for the loss between a student network (a network model with poor performance), a teacher network...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Electronics (Basel) Ročník 11; číslo 7; s. 1066
Hlavní autoři: Zhao, Ming, Li, Meng, Peng, Sheng-Lung, Li, Jie
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.04.2022
Témata:
20th century
Accuracy
Algorithms
Deep learning
Distillation
Knowledge
Machine learning
Model accuracy
Neural networks
Power consumption
Probability distribution
Teachers
ISSN:2079-9292, 2079-9292
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In order to solve the problem of large model computing power consumption, this paper proposes a novel model compression algorithm. Firstly, this paper proposes an interpretable weight allocation method for the loss between a student network (a network model with poor performance), a teacher network (a network model with better performance) and real label. Then, different from the previous simple pruning and fine-tuning, this paper performs knowledge distillation on the pruned model, and quantifies the residual weights of the distilled model. The above operations can further reduce the model size and calculation cost while maintaining the model accuracy. The experimental results show that the weight allocation method proposed in this paper can allocate a relatively appropriate weight to the teacher network and real tags. On the cifar-10 dataset, the pruning method combining knowledge distillation and quantization can reduce the memory size of resnet32 network model from 3726 KB to 1842 KB, and the accuracy can be kept at 93.28%, higher than the original model. Compared with similar pruning algorithms, the model accuracy and operation speed are greatly improved.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics11071066