Deep learning model training method, image recognition method, device and equipment

• Main Authors: DU YUNING, WEI SHENGYU, GAO TINGQUAN, CUI CHENG
• Format: Patent
• Language: Chinese; English
• Published: 27.05.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention provides a training method of a deep learning model, and relates to the technical field of artificial intelligence, in particular to the technical field of deep learning and the technical field of computer vision. According to the specific implementation scheme, sample data are input into a deep learning model, at least one piece of output feature information is obtained, and each piece of output feature information corresponds to one convolutional layer; according to the at least one piece of output feature information, at least one piece of correlation information is obtained, and each piece of correlation information is used for representing correlation among a plurality of convolution channels in one convolution layer; obtaining a first loss value according to the at least one piece of correlation information; and training a deep learning model according to the first loss value. The invention further provides an image recognition method and device, electronic equipment and a storage medium.