Recently, all the world countries have focused on protecting human health and combatting the COVID-19 outbreak. It has caused a destructive effect on human health and daily life. Many people have been infected and have died in all around the world. It is critical to control and prevent the spread of COVID-19 disease by applying quick alternative diagnosis techniques. Although the laboratory test has been applied widely in the diagnostic tool, recent findings suggest that the application of X-ray and computed tomography (CT) images and pre-trained deep CNN models can help in the accurate detection of this disease. In this study, we propose a model for COVID-19 diagnosis, applying a deep CNN technique based on using raw chest X-ray images belonging to COVID-19 patients and can be accessed publicly on GitHub. 50 positive and 50 negative COVID-19 X-ray images for training and 20 positive and 20 negative images for testing phases are included. Since the classification of X-ray images need to deep architecture due to cope with the complicated structure of images, we apply the five different architectures of well-known pre-trained deep CNN models such as the VGG16, VGG19, ResNet, DenseNet, and InceptionV3. The pre-trained VGG16 model can detect COVID-19 from non-COVID-19 cases with the highest classification performance as 80% accuracy among the other four proposed models and can be used as a helping tool in the department of radiology. In the proposed model, a limited dataset of COVID19 X-ray images is used, and it can provide more accurate performance if the number of instances in the dataset increases.