The inference operation optimization of an improved LeNet-5 convolutional neural network and its FPGA hardware implementation

Wang, Jian; Huang, Qiong; Liu, Jiang

doi:10.1109/3cbit57391.2022.00068

Cited by 2 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we compare our work with other FPGA implementations targeting similar datasets and provide a reasonable summary of our implementation results, as shown in Table I. In the study [29], they reduced the scale of the LeNet-5 model using partial 1-bit quantization for convolution and pooling layers. They generated IP using HLS for deployment on an FPGA to recognize MNIST handwritten digits.…”

Section: Results and Analysismentioning

confidence: 99%

Hardware accelerator for high accuracy sign language recognition with residual network based on FPGAs

Yang,

Li,

Hao

et al. 2024

IEICE Electron. Express

View full text Add to dashboard Cite

The ResNet series of networks has demonstrated powerful capabilities in the fields of object detection and image classification, garnering increasing attention from researchers. However, due to their deep network architectures, accelerator development based on FPGA faces challenges associated with limited on-chip resources and lengthy design cycles. This paper presents a versatile hardware acceleration system based on FPGA, achieving optimization through both hardware implementation and software inference architecture. The system reduces network complexity by employing techniques such as inter-layer fusion and dynamic quantization, while enhancing hardware resource utilization through channel parallelism and tightly-pipelined hardware design principles. By configuring and reusing computation units, the forward inference process of ResNet series networks can be rapidly deployed on FPGA, shortening the development and validation cycles. The proposed system is validated using the ResNet-18 model on a PYNQ-Z2 development board within a gesture recognition application scenario. The overall power consumption of the system is 2.136W, with hardware inference accuracy reaching 98.87%.

show abstract

Section: Results and Analysismentioning

confidence: 99%