Generative Adversarial Networks (GANs) are powerful generative models that achieved strong results, mainly in the image domain. However, the training of GANs is not trivial, presenting some challenges tackled by different strategies. Evolutionary algorithms, such as COEGAN, were recently proposed as a solution to improve the GAN training, overcoming common problems that affect the model, such as vanishing gradient and mode collapse. In this work, we propose an evaluation method based on t-distributed Stochastic Neighbour Embedding (t-SNE) to assess the progress of GANs and visualize the distribution learned by generators in training. We propose the use of the feature space extracted from trained discriminators to evaluate samples produced by generators and from the input dataset. A metric based on the resulting t-SNE maps and the Jaccard index is proposed to represent the model quality. Experiments were conducted to assess the progress of GANs when trained using COEGAN. The results show both by visual inspection and metrics that the Evolutionary Algorithm gradually improves discriminators and generators through generations, avoiding problems such as mode collapse.

翻译：在这项工作中,我们提议了一种基于分散式存储式邻居嵌入式(t-SNE)的评估方法,以评估GANs的进展,并对发电机在培训中学会的分布进行视觉化分析。我们提议利用从经过训练的制导器中提取的地貌空间来评估发电机生产的样品和输入数据集。根据所产生的t-SNE地图和Jacccard指数提出的一个指标来代表模型质量。我们进行了实验,以评估使用COEGAN培训时GANs的进展。通过视觉检查和测量,结果显示,进化Algorithm 逐渐在几代人之间改进了制导器和发电机,避免了模式崩溃等问题。