A brain tumor is the growth of abnormal cells in the tissues of brain. It affects a large number of people of different ages, worldwide. Magnetic Resonance Imaging (MRI) is the most operative and widely used technique for brain tumor detection because it provides bette r contrast images of the brain. However, the complexity of the problem, manual classification process, requirement of skilled medical practitioners, and a huge amount of MRI scan data are the major factors thwarting the timely classification of tumor vs. n on - tumor. Early detection of brain tumors is possible by accurately applying machine learning with the aim to save time, cost, and human life. Recently, deep machine learning via transfer learning techniques was found to be highly effective for classificat ion tasks. A tumor diagnosis application is presented with a VGG - 19 - based deep learning model by applying transfer learning of knowledge. Five - fold cross - validation of the model demonstrated 88% accuracy along with a 0.881 F1 score. The application could b e utilized as a successful tool aid for oncologists and radiologists in the clinical diagnostics process.