Generative Adversarial Networks can be used to generate clear images, but in different domains of the image conversion, for example, a picture from a man to a woman, or from hair to baldness, many methods use multiple models to transform input images rather than single model, which may cause the artifacts. There is no quantitative and qualitative way to evaluate the experimental results. Based on the idea of Generative Adversarial Networks, this paper can use a single model to convert multiple domains of images. After the conversion is completed, the pre-training is used to classify the images. The experimental results show that the method can realize image conversion between multiple domains and can better evaluate the experimental results.

We propose a method to prepare for developing the quality of the reconstructing objects from edge detection. We know that some conditional generative adversarial networks like pix2pix, learn a loss function to train the mapping from input image and output image. In case of using single mapping, we cannot guarantee that all samples in X and all samples in the Y are reasonably corresponding. So, we suppose to utilize bijection and we make the optimization for the pix2pix'U-net, which can develop our model to reconstruct objects from edge detection needing to be repaired. These can let our image generated by edge detection with our method get less probability of mode collapse and ensure the image style more similar to samples.

Graph has been widely used in complex network applications modeling, and the asynchronous graph processing model is superceding the BSP model because of its better convergence speed. However, the asynchronous GAS model proposed by PowerGraph usually results in irregular and unpredictable communication patterns as well as vertex-scale barriers, so it is difficult for programmers to optimize codes. To address these challenges, we propose LMCC, an improved message management approach including lazy pull-message model and vertex-oriented centralized cache, which can reduce communication cost in terms of message quantity, and reduce the number of computation iterations in turn, without compromising the accuracy of application results. Based on the deep investigation of the GAS phases, LMCC is designed to be totally transparent to user applications. Experimental results show that LMCC can deliver speedup for various types of graph computing benchmarks ranging from 129% to 271%.