Performance of Resnet-16 and Inception-V4 Architecture to Identify Covid-19 from X-Ray Images

Covid-19 has become a big challenge across the world and there has been an urgent need for breakthroughs in clinical research, vaccine discoveries/trial and pharmaceutical technologies. Symptom identification with the use of machine learning frameworks and strategies can greatly pave way for rapid control and assessments that eventually can help to contain virus outbreaks. We compare performance of two convolutional neural networks namely ResNet-16 and Inception-v4 for classification of X-ray images as Covid-19 or non-Covid-19. Results inferred the model performance is around 83% with Inception-v4, which is considerably a deeper network than ResNet-16