Luca Battiato
Tensorflow-driven neural network quantization for resource-constrained devices.
Rel. Luciano Lavagno, Mihai Teodor Lazarescu. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Elettronica (Electronic Engineering), 2020
|
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (4MB) | Preview |
Abstract: |
Design space exploration with the most promising discretization techniques offered by Tensorflow against some Neural Networks belonging to CNN, MLP and LSTM families. The quantization with different representational precision is performed using a Post-training approach with already trained Models, and with a Quantization-aware training approach with a comprehensive training session from scratch. The results collected demonstrate the effectiveness of these Techniques that can ensure minimal accuracy loss with interesting improvement in Model compression and, during the deploying on resource-constrained devices, hardware accelerations. |
---|---|
Relatori: | Luciano Lavagno, Mihai Teodor Lazarescu |
Anno accademico: | 2020/21 |
Tipo di pubblicazione: | Elettronica |
Numero di pagine: | 74 |
Soggetti: | |
Corso di laurea: | Corso di laurea magistrale in Ingegneria Elettronica (Electronic Engineering) |
Classe di laurea: | Nuovo ordinamento > Laurea magistrale > LM-29 - INGEGNERIA ELETTRONICA |
Aziende collaboratrici: | Politecnico di Torino |
URI: | http://webthesis.biblio.polito.it/id/eprint/16621 |
Modifica (riservato agli operatori) |