Iteration method of image reconstruction model and image reconstruction method
An image reconstruction and model technology, applied in the field of data processing, can solve problems such as large-scale jitter and unstable loss function convergence, and achieve the effect of speeding up efficiency, overcoming the instability of loss function convergence, and achieving iterative effect.
Pending Publication Date: 2021-12-07
SHANGHAI BIREN TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The present invention provides an iterative method of an image reconstruction model and an image reconstruction method, which are used to overcome the defects of unstable convergence or large jitter of the loss function in the iterative process of the neural network in the prior art
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
[0047]In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention , but not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0048] Some of the current image reconstruction tasks use image reconstruction models based on deep neural networks for image reconstruction, and when using image reconstruction models based on deep neural networks for image reconstruction, it is necessary to iterate the neural network. In the iterative process of the neural network, it is necessary to The loss function performs iterative 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
Login to View More Abstract
The invention provides an iteration method of an image reconstruction model and an image reconstruction method; the method comprises the steps: carrying out the first iteration of the image reconstruction model based on original data, and obtaining a first weight value and a first loss function value of the image reconstruction model; if the first loss function value indicates that convergence is abnormal, replacing a first weight value of the image reconstruction model with a normal weight value, and performing second iteration on the image reconstruction model after the weight value replacement until a second loss function value obtained by the second iteration indicates that convergence is normal; and carrying out first iteration on the image reconstruction model after the second loss function value indicates normal convergence, wherein the learning rate of the first iteration is larger than that of the second iteration, and the normal weight value is the weight value obtained by iteration with the last loss function value indicated normal convergence. According to the method, the defect that the model iteration effect is poor due to unstable convergence of the loss function is overcome, and the iteration efficiency and the iteration effect are improved.
Description
technical field [0001] The invention relates to the technical field of data processing, in particular to an iterative method for an image reconstruction model and an image reconstruction method. Background technique [0002] Some of the current image reconstruction tasks use image reconstruction models based on deep neural networks for image reconstruction, and when using image reconstruction models based on deep neural networks for image reconstruction, the neural network needs to be iterated, and the loss function needs to be adjusted during the neural network iteration. Iterative convergence. Due to various reasons in the convergence, the convergence of the loss function may eventually lead to unstable convergence. The repeated occurrence of this situation will have a great impact on the iterative effect of the neural network. [0003] In the current neural network iteration process, the derivative of the loss function value to the weight value is obtained through the cha...
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): G06T11/00G06N3/04G06N3/08
CPCG06T11/003G06N3/04G06N3/08G06T2211/424
Inventor 不公告发明人
Owner SHANGHAI BIREN TECH CO LTD