Szczegóły publikacji
Opis bibliograficzny
Retrain or not retrain? – efficient pruning methods of deep CNN networks / Marcin PIETROŃ, Maciej WIELGOSZ // W: Computational Science - ICCS 2020 : 20th International Conference : Amsterdam, The Netherlands, June 3–5, 2020 : proceedings, Pt. 3 / eds. Valeria V. Krzhizhanovskaya, [et al.]. — Cham : Springer Nature Switzerland, cop. 2020. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 12139. Theoretical Computer Science and General Issues ; ISSN 0302-9743). — ISBN: 978-3-030-50419-9; e-ISBN: 978-3-030-50420-5. — S. 452–463. — Bibliogr. s. 462–463, Abstr. — Publikacja dostępna online od: 2020-06-15
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 129159 |
|---|---|
| Data dodania do BaDAP | 2020-06-24 |
| Tekst źródłowy | URL |
| DOI | 10.1007/978-3-030-50420-5_34 |
| Rok publikacji | 2020 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | 20th International Conference on Computational Science |
| Czasopisma/serie | Theoretical Computer Science and General Issues, Lecture Notes in Computer Science |
Abstract
Nowadays, convolutional neural networks (CNN) play a major role in image processing tasks like image classification, object detection, semantic segmentation. Very often CNN networks have from several to hundred stacked layers with several megabytes of weights. One of the possible techniques to reduce complexity and memory footprint is pruning. Pruning is a process of removing weights which connect neurons from two adjacent layers in the network. The process of finding near optimal solution with specified and acceptable drop in accuracy can be more sophisticated when DL model has higher number of convolutional layers. In the paper few approaches based on retraining and no retraining are described and compared together.