Using deep compression on PyTorch models for autonomous systems

Name: Using deep compression on PyTorch models for autonomous systems
Author: Doğan, Eren, Uğurdağ, Hasan Fatih, Ünlü, Hasan

İsim	Using deep compression on PyTorch models for autonomous systems
Yazar	Doğan, Eren, Uğurdağ, Hasan Fatih, Ünlü, Hasan
Basım Tarihi:	2022
Basım Yeri	- IEEE
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-166545092-8
Kayıt Numarası	e84b9b68-0a27-4930-bec3-46f6fc5df6cc
Lokasyon	Electrical & Electronics Engineering
Tarih	2022
Örnek Metin	Applications of artificial neural networks on low-cost embedded systems and microcontrollers (MCUs), has recently been attracting more attention than ever. Since MCUs have limited memory capacity as well as limited compute-speed compared to workstations, employment of current deep learning algorithms on MCUs becomes more practical with the help of model compression. This makes MCUs common and practical alternative solution for autonomous systems. In this paper, we add model compression, specifically Deep Compression, to an existing work, which efficiently deploys PyTorch models on MCUs, in order to increase neural network speed and save electrical power. First, we prune the weight values close to zero in convolutional and fully connected layers. Secondly, the remaining weights and activations are quantized to 8-bit integers from 32-bit floating-point. Finally, forward pass functions are compressed using special data structures for sparse matrices, which store only nonzero weights. In the case of the LeNet-5 model, the memory footprint was reduced by 12.5x, and the inference speed was boosted by 2.6x.
DOI	10.1109/SIU55565.2022.9864848

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Using deep compression on PyTorch models for autonomous systems

Yazar Doğan, Eren, Uğurdağ, Hasan Fatih, Ünlü, Hasan

Basım Tarihi 2022

Basım Yeri - IEEE

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-166545092-8

Kayıt Numarası e84b9b68-0a27-4930-bec3-46f6fc5df6cc

Lokasyon Electrical & Electronics Engineering

Tarih 2022

Örnek Metin Applications of artificial neural networks on low-cost embedded systems and microcontrollers (MCUs), has recently been attracting more attention than ever. Since MCUs have limited memory capacity as well as limited compute-speed compared to workstations, employment of current deep learning algorithms on MCUs becomes more practical with the help of model compression. This makes MCUs common and practical alternative solution for autonomous systems. In this paper, we add model compression, specifically Deep Compression, to an existing work, which efficiently deploys PyTorch models on MCUs, in order to increase neural network speed and save electrical power. First, we prune the weight values close to zero in convolutional and fully connected layers. Secondly, the remaining weights and activations are quantized to 8-bit integers from 32-bit floating-point. Finally, forward pass functions are compressed using special data structures for sparse matrices, which store only nonzero weights. In the case of the LeNet-5 model, the memory footprint was reduced by 12.5x, and the inference speed was boosted by 2.6x.

DOI 10.1109/SIU55565.2022.9864848