Picture generation method based on depth learning and generative adversarial network

Abstract

The invention discloses a picture generation method based on depth learning and a generative adversarial network. The method comprises steps that (1), a picture database is established, multiple real pictures are collected and are further classified and marked, and each picture has a unique class label k corresponding to the each picture; (2), the generation network G is constructed, a vector combined by a random noise signal z and the class label k is inputted to the generation network G, and generated data is taken as input of a discrimination network D; (3), the discrimination network D is constructed, and a loss function of the discrimination network D comprises a first loss function used for determining true and false pictures and a second loss function used for determining picture classes; (4), the generation network is trained; (5), needed pictures are generated, the random noise signal z and the class label k are inputted to the generation network G trained in the step (4) to acquire pictures in a designated class. The method is advantaged in that not only can the pictures can be generated, but also the designated generation picture classes can be further realized.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a deep learning-based picture generation method and a generated confrontation network. Background technique [0002] Facial expression is the most intuitive reflection of human emotional state, an important medium to convey human physical state and emotional state, and the main communication method besides language communication. In the process of human-computer interaction, the generation of emoticons can undoubtedly provide people with more convenient communication and services. [0003] As an important field of machine learning at present, deep learning has important applications in image recognition, speech analysis and other directions. Deep learning evolved from neural networks. So far, people have designed a variety of effective network structures for various problems such as classification, detection, and recognition. Among them, in many fields such as fac...

AI Technical Summary

Problems solved by technology

However, although the generative confrontation network can generate near-real pictures, it cannot generate the required pictures according to the category, which limits the application of the generative confrontation network

Images