The study of the mechanical properties and behavior of materials, as well as stress and strain fields, has been carried out using methods such as experiments, numerical methods, and precise mathematical solutions over the decades. In recent years, machine learning, and especially deep learning, have become one of the most commonly used methods in various engineering fields. One of its important applications is the prediction of material behavior in numerous structures. These methods have drawn significant attention due to their rapid execution, apposite accuracy, and implementation convenience, and are used as an alternative or supplementary tool for traditional analysis methods. Using the machine learning method, in case the problems are properly characterized, they can provide a much more powerful tool in a machine learning process compared to other tools. The purpose of this paper is to predict the stress field and maximum stress on a perforated plate under static loading using a deep learning method based on a conditional adversarial generative network (CGANs) and to quantify the results using an image processing method. Also, at the end, the numerical results obtained from this model are extracted and compared with the results attained from finite element analysis to evaluate the accuracy of the proposed model.