Classification model training method and device, classification method and device, medium and equipment
A classification model and training method technology, applied in the field of deep learning, can solve problems such as expensive, consuming a lot of manpower and material resources, and unable to realize the supervised training process, so as to reduce time and labor costs, ensure training accuracy, and reduce manual setting of labels cost effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] figure 1 It is a schematic flow chart of a classification model training method provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of weakly supervised model training on the basis of a small number of labeled samples. This method can be classified by the classification model provided by the embodiment of the present invention. The training device of the model can be implemented by means of software and / or hardware, and the device can be integrated into an electronic device such as a computer or a server. The method specifically includes the following steps:
[0031] S110. Acquire first sample data without a classification label set, input the first sample data into a pre-trained basic classification model, and determine the probability of setting a preset classification label for the first sample data, wherein, The basic classification model is trained based on the second sample data with preset classification labels.
[0032]...
Embodiment 2
[0067] figure 2 It is a schematic flow chart of a training method for a classification model provided in Embodiment 2 of the present invention. On the basis of the above embodiments, optimization is carried out. The method specifically includes:
[0068] S210. Acquire first sample data without a classification label set, input the first sample data into a pre-trained basic classification model, and determine the probability of setting a preset classification label for the first sample data, wherein, The basic classification model is trained based on the second sample data with preset classification labels.
[0069] S220. Based on the preset confidence threshold and the probability corresponding to the first sample data, determine a rejected sample, and remove the rejected sample from the first sample data to obtain a received sample set.
[0070] S230. For the first sample data in the received sample set, determine the weight of the first sample data based on the probability...
Embodiment 3
[0079] image 3 It is a schematic flow chart of a classification method provided by the embodiment of the present invention. This embodiment is applicable to the situation where the data to be classified is classified and processed. The method can be executed by the classification device provided by the embodiment of the present invention, and specifically includes the following steps:
[0080] S310. Obtain the data to be classified.
[0081] S320. Input the data to be classified into the target classification model, and determine the classification result of the data to be classified based on the output of the target classification model, wherein the target classification model is based on the classification provided in the above embodiment The training method of the model is trained.
[0082] Wherein, the data to be classified can be any one of image data, text data, audio data or video data, and the pre-trained classification model is determined according to the type of da...
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