Unlock instant, AI-driven research and patent intelligence for your innovation.

Method, device and equipment for training model, medium and product

A technology for training models and models, which is applied in the computer field and can solve problems such as poor model training effects.

Active Publication Date: 2021-09-14
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the model training process of model compression, it is often necessary to pre-set fixed resources for model training. If the setting of fixed resources is unreasonable, it will lead to the problem of poor model training effect.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device and equipment for training model, medium and product
  • Method, device and equipment for training model, medium and product
  • Method, device and equipment for training model, medium and product

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0020] It should be noted that, in the case of no conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments.

[0021] Such as figure 1 As shown, the system architecture 100 may include a stu...

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

No PUM Login to View More

Abstract

The invention provides a method, a device, equipment, a medium and a product for training a model, relates to the technical field of computers, in particular to an artificial intelligence technology, and can be applied to a model compression scene in deep learning. According to the specific implementation scheme, the method comprises the steps of: obtaining a to-be-trained student model set; for each to-be-trained student model in the to-be-trained student model set, determining a teacher model corresponding to the to-be-trained student model; sending training data to each teacher model, and receiving a soft label set returned by each teacher model based on the training data; and based on the soft label set, training each to-be-trained student model in the to-be-trained student model set to obtain each trained student model. According to the implementation mode, the model training effect can be improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, in particular to artificial intelligence technology, which can be applied to model compression scenarios in deep learning. Background technique [0002] At present, deep neural networks have been widely used in computer vision, natural language processing and other technical fields. Due to the high computational complexity required by deep neural networks, the memory requirements are large, which makes it difficult to apply deep neural networks to small devices. [0003] Nowadays, model compression technology is usually used to reduce the computational complexity of deep neural network models based on compressing the teacher model into a student model. However, in the model training process of model compression, it is often necessary to pre-set fixed resources for model training. If the setting of fixed resources is unreasonable, it will lead to the problem of poor model training effe...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N20/00
CPCG06N20/00
Inventor 刘吉吴志华董大祥王曦巩伟宝于佃海李兴建杨亚鑫窦德景
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD