A method and device for obtaining a convolution neural network
A convolutional neural network and branching technology, applied in the field of obtaining convolutional neural networks, can solve problems such as time-consuming and laborious, and achieve the effect of reducing labor burden
Active Publication Date: 2019-03-08
BEIJING KUANGSHI TECH
View PDF9 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In the existing technology, different sampling parameters can be designed for down-sampling or up-sampling. However, there is currently no specific theoretical basis to prove which sampling parameter is better, so the design of the semantic segmentation model still needs manual work. try, time consuming
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
[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.
[0054] It should be noted that like numerals and let...
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 relates to the technical field of image processing and provides a method and device for obtaining a convolution neural network, wherein at least one sampling structure is included in theconvolution neural network, each sampling branch of the sampling structure samples the feature map generated in the convolution neural network according to different sampling parameters, and the sampled feature map is obtained by weighted averaging the sampling results of each sampling branch according to the weighted coefficients of each sampling branch. The method comprises the following stepsof determining the weighted coefficients of each sampling branch of each sampling structure by training a convolution neural network; after the training, determining the convolution neural network which contains the sampling branch with the largest weighting coefficient to be the convolution neural network which can be used for image processing task. The above method can automatically select the best sampling mode for the current training set, effectively reduces the artificial burden in the process of model design and has wider application scope, and the performance of the obtained convolution neural network is better.
Description
technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for obtaining a convolutional neural network. Background technique [0002] Image semantic segmentation is one of the basic tasks of computer vision. It is an important part of computer understanding of images or videos. Its purpose is to predict its category label for each pixel of the input image, so theoretically requires the predicted image size of the output Same size as input image. Most of the existing semantic segmentation methods are based on convolutional neural networks, and in order to allow the network to obtain a larger receptive field and reduce the amount of calculation of the model, the network often first downsamples the image (downsample), and finally uses upsampling ( upsample) to restore the size of the output image so that it is consistent with the input image. [0003] In the existing technology, different sampling par...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 郭梓超
Owner BEIJING KUANGSHI TECH