Method for training separable convolutional network, road side equipment and cloud control platform
A convolution network and convolution technology, applied in the computer field, can solve problems such as cumbersome model design, limited equipment resource conflicts, etc.
Pending Publication Date: 2021-09-03
APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In order to meet industrial needs, it is often necessary to design the model to be very cumbersome, but this often creates a conflict with the limited equipment resources of the application scenario
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0023] Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
[0024] figure 1 is a schematic diagram 100 showing a first embodiment according to the present disclosure. The method for training a separable convolutional network includes the following steps:
[0025] S101. Acquire a set of batch training samples.
[0026] In this embodiment, the subject of execution of the method for training a separable convolutional network may...
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
Login to View More Abstract
The invention provides a method for training a separable convolutional network, road test equipment and a cloud control platform, and relates to the technical field of computers, in particular to intelligent traffic and computer vision technologies. The specific implementation scheme is as follows: acquiring a batch training sample set comprising a second number of sample images and corresponding sample labels; generating a local region block set of a sliding window of a second initial convolution kernel corresponding to the batch of training sample sets; respectively generating a first number of parallel fusion convolution kernels for each local region block in the local region block set; carrying out convolution on the corresponding local region blocks based on the generated first number of parallel fusion convolution kernels, and generating feature maps corresponding to the second number of sample images in the batch of training sample sets; and adjusting the first initial convolution kernel and the first number of parallel second initial convolution kernels according to the difference between the generated feature map and the corresponding sample label.
Description
technical field [0001] The present disclosure relates to the field of computer technology, in particular to artificial intelligence, computer vision technology and intelligent transportation, and in particular to a method for training a separable convolutional network, a roadside device and a cloud control platform. Background technique [0002] With the rapid development of artificial intelligence and computer vision technology, deep learning neural network is highly sought after by the industrial market because of its superior performance. In order to meet industrial needs, it is often necessary to design the model to be very cumbersome, but this often creates a conflict with the limited device resources of the application scenario. [0003] In the prior art, a lightweight neural network architecture specially aimed at resource-constrained terminal devices is often adopted, and its core is depthwise separable convolution (Depthwise Convolution). Contents of the invention...
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
Login to View More IPC IPC(8): G06N3/08G06N3/04G06K9/00G06K9/46G06K9/62
CPCG06N3/084G06N3/048G06N3/045G06F18/22
Inventor 夏春龙
Owner APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECH CO LTD