Heterogeneous acceleration system and method based on ctpn network

A technology for accelerating systems and networks, applied to biological neural network models, architectures with a single CPU, neural architectures, etc., can solve problems such as hardware acceleration is difficult to achieve, and achieve shortened inference time, strong versatility, and good acceleration performance Effect

Active Publication Date: 2022-05-06
SHANGHAI JIAOTONG UNIV +1
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, its complex network structure makes hardware acceleration difficult to achieve due to resource constraints, so implementing heterogeneous acceleration for this network is an effective solution

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Heterogeneous acceleration system and method based on ctpn network
  • Heterogeneous acceleration system and method based on ctpn network
  • Heterogeneous acceleration system and method based on ctpn network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] The invention includes a CPU-FPGA heterogeneous execution optimization sub-graph segmentation method for CTPN and similar structure networks. The heterogeneous execution optimization subgraph segmentation method of the present invention balances the consumption of hardware resources and the transmission cost between hardware, and adjusts the functions of the network layer on the execution device, so that both FPGA and CPU have better acceleration effects.

[0045] The heterogeneous execution optimization subgraph segmentation method divides the CTPN network into three main subgraphs: figure 1 ,son figure 2 And child image 3 . The subgraphs run on different processing devices and exchange data. The optimized subgraph segmentation and heterogeneous execution can reduce the overall execution time of the CTPN network and improve the acceleration performance.

[0046]The heterogeneous execution of the present invention refers to the joint execution of the accelerator in...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention provides a heterogeneous acceleration system and method based on a CTPN network, including a CPU end and an FPGA end; the FPGA end includes a first sub-graph and a second sub-graph, and the CPU end includes a third sub-graph; The first sub-graph includes the CTPN network CNN part, the second sub-graph includes the RNN part, and the third sub-graph includes the rest of the CTPN network; the first sub-graph and the second sub-graph are executed on the FPGA side, and the second sub-graph is executed on the FPGA side. The three subgraphs are executed on the CPU side; the output of the FPGA side is used as the input of the third subgraph; the CPU side finally implements network inference and obtains the final result. The present invention can greatly increase the inference speed of the CTPN network with little decrease in precision, and enables the accelerator to better realize the function of real-time scene character recognition.

Description

technical field [0001] The present invention relates to the field of neural network accelerators, in particular to a CTPN network-based heterogeneous acceleration system and method. Background technique [0002] Connectionist Text Proposal Network (CTPN), a neural network proposed in 2016 for scene text recognition, is actually a neural network based on CNN+RNN structure. Among them, CNN is used to extract deep features, and RNN is used for character sequence feature recognition. This network takes advantage of the respective advantages of CNN and RNN. RNN also uses bidirectional LSTM (BiLSTM) to recognize and infer text from different directions of the picture, which greatly improves the accuracy of text detection. Since various applications of scene text recognition require network recognition and inference to be as fast as possible, it is particularly important to implement hardware acceleration for CTPN networks. However, its complex network structure makes hardware ac...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F15/78G06N3/04
CPCG06F15/7871G06N3/044G06N3/045
Inventor 蒋剑飞蔡亮郭怡良董峰虞科华陈可
Owner SHANGHAI JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap