Diagnosis of Covid-19 disease is a necessity for its prevention and control. The use of deep learning methods has been considered a fast and accurate method. In this paper, by combining three well-known pre-trained networks in parallel, an attempt was made to distinguish coronavirus-infected samples from healthy samples. Negative log-likelihood loss function has been used for model training. CT scan images in the SARS-CoV-2 dataset were used for diagnosis. The SARS-CoV-2 dataset contains 2482 images of lung CT scans, of which 1252 images belong to Covid-19 infected samples. The proposed model was able to be about 97% accurate.