Coronavirus Disease-2019 (COVID-19) pandemic continues to have a severe impact on the worldwide public's health and well-being. Effective screening of contaminated individuals is a significant step in the fight against COVID-19, with radiologic evaluation employing chest radiography being one of the primary screening modalities. In preliminary research, it was discovered that patients with COVID-19 contamination have anomalies in chest radiography imaging. The goal of this work is to develop a deep-learning algorithm for early diagnosis of COVID-19 and pneumonia lung infections using CXR images. Methods: A deep transfer learning technique is given for image categorization using an improved Residual Network model with 53 layers, which is a variation of the ResNet-50 model. The model is evaluated using the COVIDx dataset, which contains 13975 CXR pictures, as well as the Kermany dataset, which has 5856 CXR images. 80% of the photos in this image collection are used for training, while 20% are utilised for testing. Python is used for implementation to illustrate the efficacy of the suggested paradigm. The performance results are analysed and compared to pre-trained models such as GoogLeNet, ResNet18, and DensNet121. Findings: On the Kermany dataset, the suggested model achieves 98.1% accuracy, 98.8% precision, and 98.8% recall, while on the COVIDx dataset, it achieves 97.1% accuracy, 98.9% recall, 95.7% specificity, and 94.5% precision, which is superior to the most advanced models addressed in the literature. Novelty: We have added three layers to ResNet50, making it a ResNet50+3 layer architecture. These three extra layers solve the vanishing gradient problem in the ResNet50 architecture, making it easier to train. According to the findings of the complete investigation, the suggested model not only surpasses most classifiers such as GoogLeNet, ResNet50, and DenseNet121 in terms of accuracy, precision, and recall, but it is also a very versatile model that works well on varied datasets

Machine Learning, Deep Learning, Covid-19, Pneumonia, x-ray images, googlenet, resnet, densenet, vgg.