Method and device for acquiring target network model, computer equipment and storage medium

The invention relates to the technical field of artificial intelligence algorithms, in particular to a method and device for obtaining a target network model, computer equipment and a storage medium, and the method comprises the steps: obtaining a teacher network model and a student network model, the student network model being a simplified model of the teacher network model; in the student network model, adding a residual structure between two initial adjacent convolutional layers to obtain a target network model, so that the training data set passes through the first convolutional layer in the student network model to obtain a convolutional data set; a part of the convolution data set is weighted to the remaining convolution data set after being processed by the residual structure, so that the local features of the convolution data set are enhanced, then the convolution data set is input into the second convolution layer, and feature enhancement is performed on the data through the added residual structure