Exploring Efficient Acceleration Architecture for Winograd-Transformed Transposed Convolution of GANs on FPGAs

Exploring Efficient Acceleration Architecture for Winograd-Transformed Transposed Convolution of GANs on FPGAs

The acceleration architecture of transposed convolution layers is essential since transposed convolution operations, as critical components in the generative model of generative adversarial networks, are computationally intensive inherently. In addition, the pre-processing of inserting and padding w...

Full description

Bibliographic Details
Main Authors: Xinkai Di, Hai-Gang Yang, Yiping Jia, Zhihong Huang, Ning Mao
Format: Article
Language:English
Published: MDPI AG 2020-02-01
Series:Electronics
Subjects:
generative adversarial networks (gans)
transposed convolution
winograd
fpga
acceleration architecture
processing units
Online Access:https://www.mdpi.com/2079-9292/9/2/286

Internet

https://www.mdpi.com/2079-9292/9/2/286

Similar Items