Convolutional neural network model training method and device and computer readable storage medium
A convolutional neural network and model training technology, applied in the field of convolutional neural network model training, can solve problems such as misjudgment of target areas
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0094] In order to solve the technical problem of misjudgment of a target area in the prior art, an embodiment of the present disclosure provides a method for training a convolutional neural network model. like Figure 1a As shown, the convolutional neural network model training method mainly includes the following steps S11 to S12. in:
[0095] Step S11: Constructing a convolutional neural network, wherein the convolutional layer of the convolutional neural network includes a plurality of parallel convolution kernels, and each convolution kernel corresponds to a training channel.
[0096] Among them, Convolutional Neural Networks (CNN) is a type of feed-forward neural network that includes convolutional calculations and has a deep structure, mainly including an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. Also, a convolutional neural network can include multiple convolutional layers. In this paper, the convolutional neur...
Embodiment 2
[0119] In order to solve the technical problem of low accuracy rate of target area determination in the prior art, the embodiment of the present disclosure also provides a target area determination method, such as figure 2 shown, including:
[0120] S21: Obtain an image to be recognized.
[0121] Among them, the image to be recognized can be obtained in real time through the camera. Or obtain a pre-stored image to be recognized locally.
[0122] S22: Input the image to be recognized into the convolutional neural network model.
[0123] Wherein, the convolutional neural network model is trained by using the convolutional neural network model training method described in the first embodiment above, and the specific training process is referred to the first embodiment above.
[0124] S23: Predict and obtain multiple feature data through multiple training channels of the convolutional neural network model.
[0125] Among them, a training channel corresponds to predicting a fe...
Embodiment 3
[0157] In order to solve the technical problem of low accuracy rate of target area determination in the prior art, an embodiment of the present disclosure provides a convolutional neural network model training device. The device can execute the steps in the embodiment of the convolutional neural network model training method described in the first embodiment above. like image 3 As shown, the device mainly includes: a network construction module 31 and a model training module 32; wherein,
[0158] The network construction module 31 is used to construct the convolutional neural network, wherein the convolutional layer of the convolutional neural network includes a plurality of parallel convolution kernels, and each convolution kernel corresponds to a training channel;
[0159] The model training module 32 is used to input the training sample set into the convolutional neural network, and independently trains each training channel according to the training sample set until meet...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com