Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Optimization method of HarDNet-Lite in embedded platform

An optimization method and embedded technology, which is applied in the optimization field of HarDNet-Lite on embedded platforms, can solve the problems of slow model forward reasoning, weak computing power of embedded devices, and failure of network models to be loaded and run. The effect of increasing the inference speed, reducing the volume size, and reducing the amount of parameters

Pending Publication Date: 2021-01-15
苏州凌图科技有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] (1) Storage problem: With the deepening of the network structure, a large number of convolution kernel weights are stored in the network, so that the storage space occupied by the model itself becomes larger and larger, even up to hundreds of megabytes, while embedded devices The storage space and memory itself are relatively limited, and network models that are too large often cannot be loaded and run;
[0005] (2) Speed ​​problem: In practical applications, the forward inference speed of the model is generally required to be on the order of milliseconds. If the network model is too complex, the amount of calculation will also increase, and the computing power of embedded devices is relatively weak, which will cause the model The speed of forward reasoning becomes very slow, ranging from a few seconds to more than ten seconds, which cannot meet the practical requirements of close to real-time

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
  • Optimization method of HarDNet-Lite in embedded platform
  • Optimization method of HarDNet-Lite in embedded platform
  • Optimization method of HarDNet-Lite in embedded platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Such as figure 1 As shown, the optimization method of HarDNet-Lite on the embedded platform includes the following five steps: 1. Build the HarDNet-Lite feature extraction network structure; 2. Use weighted FPN to fuse feature maps of different scales; 3. Generate YOLO detection head; 4. Classification and regression loss functions; 5. Deploy the model on an embedded platform. These five steps will be described in detail below.

[0041] 1. HarDNet-Lite feature extraction network structure

[0042] 1.1 The composition of HarDBlock

[0043] The HarDNet-Lite network structure is built by the basic HarDBlock. Each HarDBlock is composed of convolutional layers with different connections. A basic HarDBlock structure with 8 layers of conv...

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 invention discloses a method for optimizing HarDNet-Lite on an embedded platform, which is used for solving the problems that the existing target detection network is too complex, the operand is large, the reasoning speed on the embedded platform is low, and the positioning precision is low. The method comprises the following steps: 1) establishing a lightweight HarDNetLite feature extractionnetwork; 2) fusing feature maps of different scales by adopting a weighted FPN structure, so rich underlying detail information and high-level semantic information are fully fused; 3) generating a YOLO detection head, and placing an anchor frame generated through k-means clustering on the feature maps of different sizes to detect targets of different sizes; 4) performing end-to-end model trainingby using a classification and regression loss function; 5) deploying the trained model on an embedded platform, and carrying out target detection. The invention has the beneficial effects that the reasoning speed and the target detection precision of the HarDNet-Lite target detection network on the embedded platform are improved.

Description

technical field [0001] The invention belongs to the technical field of target detection, in particular to an optimization method of HarDNet-Lite on an embedded platform. Background technique [0002] Object detection is an important branch of computer vision, which is widely used in reality, such as video surveillance, industrial detection, face detection and many other fields. Computer vision can reduce the consumption of labor costs, which has a strong practical application significance . [0003] Since 2012, convolutional neural networks have developed rapidly, and some more powerful network structures have been proposed, such as Vgg, GoogleNet, ResNet, ResNext, DenseNet, etc. In order to obtain better performance, the number of layers of the network continues to increase, and the amount of parameters becomes larger and larger. In this way, although the performance of the network has been improved, the problem of efficiency comes with it. Efficiency The problem is mainl...

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
IPC IPC(8): G06K9/62G06N3/04
CPCG06V2201/07G06N3/045G06F18/23213G06F18/214G06F18/253
Inventor 黄文丽杨省高子昂胡鹏程金平解伟荣
Owner 苏州凌图科技有限公司
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
Eureka Blog
Learn More
PatSnap group products