Model Parallelism Optimization for CNN FPGA Accelerator
Convolutional neural networks (CNNs) have made impressive achievements in image classification and object detection. For hardware with limited resources, it is not easy to achieve CNN inference with a large number of parameters without external storage. Model parallelism is an effective way to reduc...
Main Authors: | Jinnan Wang, Weiqin Tong, Xiaoli Zhi |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-02-01
|
Series: | Algorithms |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-4893/16/2/110 |
Similar Items
-
FPGAN: An FPGA Accelerator for Graph Attention Networks With Software and Hardware Co-Optimization
by: Weian Yan, et al.
Published: (2020-01-01) -
Enhanced Efficiency 3D Convolution Based on Optimal FPGA Accelerator
by: Hai Wang, et al.
Published: (2017-01-01) -
An FPGA-Based CNN Accelerator Integrating Depthwise Separable Convolution
by: Bing Liu, et al.
Published: (2019-03-01) -
Novel CNN Accelerator Design With Dual Benes Network Architecture
by: Chun Yan Lo, et al.
Published: (2023-01-01) -
FPGA Implementation of Image Registration Using Accelerated CNN
by: Seda Guzel Aydin, et al.
Published: (2023-07-01)