Rapid training method and system for super-size image
A training method and super-sized technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of numerous parameters, long time-consuming model training, several or even more than ten hours, etc., to achieve fast and accurate training Effect
Pending Publication Date: 2022-04-12
BEIJING LUSTER LIGHTTECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] With the continuous development of deep learning technology, image detection technology based on deep learning is gradually promoted in industrial inspection. Image detection requires the use of deep learning technology for model training. The training of the network model takes a long time. Therefore, when the image size is too large, the model training for the super-sized image often takes several or even ten hours, and the cost of model iteration time is high.
[0003] The existing technical solution to solve the time-consuming model training is mainly to divide the super-sized image into small-sized images, and then perform image labeling on the multiple small-sized images after segmentation, and divide the multiple small-sized images after labeling for model training
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
[0020] In order to make the purpose, implementation and advantages of the application clearer, the following will clearly and completely describe the exemplary embodiments of the application in conjunction with the accompanying drawings in the exemplary embodiments of the application. Obviously, the described exemplary embodiments It is only a part of the embodiments of the present application, but not all the embodiments.
[0021] Based on the exemplary embodiments described in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts fall within the protection scope of the appended claims of this application. In addition, although the disclosures in this application are introduced as exemplary one or several examples, it should be understood that each aspect of these disclosures can also independently constitute a complete implementation. It should be noted that the brief description of the terms in this applicat...
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 discloses an oversize image rapid training method and system. The method comprises the following steps: receiving an input oversize image; determining a to-be-detected area on the oversize image; performing image annotation in the to-be-detected area; performing segmentation operation on the to-be-detected area subjected to image annotation according to preset parameters; the sub-graphs are marked to obtain all the marked sub-graphs; and determining all the marked sub-graphs as model training data. According to the technical scheme, super-size image training can be rapidly and accurately carried out.
Description
technical field [0001] The present application relates to the technical field of image detection, in particular to a fast training method and system for super-sized images. Background technique [0002] With the continuous development of deep learning technology, image detection technology based on deep learning is gradually promoted in industrial inspection. Image detection requires the use of deep learning technology for model training. The training of the network model takes a long time. Therefore, when the image size is too large, the model training for the super-sized image often takes several or even ten hours, and the cost of model iteration time is high. [0003] The existing technical solution to solve the time-consuming model training is mainly to divide the super-sized image into small-sized images, and then perform image labeling on the multiple small-sized images after segmentation, and divide the multiple small-sized images after labeling for model training. ...
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): G06V10/774G06K9/62
Inventor 刘红刘辉夏炎杨济铭安登奎戴志强姚毅杨艺
Owner BEIJING LUSTER LIGHTTECH