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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com