Model training method, image detection method and detection device
A model training and image detection technology, applied in the field of image processing, can solve the problems of slowing down the model convergence speed and high computational complexity, and achieve the effect of increasing the computing speed, reducing the complexity, and reducing the loss
Active Publication Date: 2021-09-07
SENSLAB INC
View PDF12 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to provide a model training method, an image detection method and a detection device to solve the problem that the existing loss function contains a log operation unit, the calculation complexity is high, and the convergence speed of the model is slowed down
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
[0072] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are part of the present invention Examples, 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. Unless otherwise defined, the technical terms or scientific terms used herein shall have the usual meanings understood by those skilled in the art to which the present invention belongs. As used herein, "comprising" and similar words mean that the elements or items appearing before the word include the elements or items listed after the word and their equivalents, without excluding other el...
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 present invention provides a kind of model training method, builds product type Focal loss function, uses described product type Focal loss function to carry out model training to neural network model and outputs trained neural network model; The construction of described product type Focal loss function The method includes the following steps: setting the weight value to solve the problem that the existing loss functions all contain log operation units, the calculation complexity is relatively high, and the convergence speed of the model is slowed down; the sample ratio balance factor α is set, and through W and α Constructing the product type Focal loss function reduces the computational complexity and improves the operation speed, and solves the problem that the contribution of the wrongly classified target individual to the loss function increases in power series, and also takes into account the correctly classified target The contribution of individuals to the loss function shows a power series decrease, so that the product type Focal loss function reflects the overall discrimination of the feature map. The invention provides an image detection method and a detection device.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a model training method, an image detection method and a detection device. Background technique [0002] Human figure detection refers to detecting whether there is a human figure in the image, extracting features from the human figure image, and detecting the human figure through the extracted features. Humanoid detection is an important research topic in computer vision, and it is widely used in intelligent video surveillance, vehicle assisted driving, intelligent transportation, intelligent robots and other fields. The mainstream humanoid detection methods are divided into statistical learning methods based on artificial image features and deep learning methods based on artificial neural networks. Deep learning methods include loss functions, which, as a means of measuring the inconsistency between model predictions and real values, are crucial for automatic paramete...
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 Patents(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/241
Inventor 龚向阳
Owner SENSLAB INC