The heart is most vital organs in the human body, and even a brief interruption in its function can have severe and life-threatening consequences. The leading cause of death globally, cardiovascular illnesses claim almost 17.1 million lives each year. Among these, cardiomyopathy represent a significant group of disorders that affect cardiac function. Cardiac magnetic resonance imaging is an essential tool for the diagnosis and management of such conditions. In this context, deep learning has emerged as a powerful technique for predicting and classifying heart diseases, including different types of cardiomyopathy. The preprocessing involved image enhancement using CLAHE and normalization to ensure computational efficiency. These processed images were then classified using a Convolutional Neural Network (CNN). The model is designed to identify and categorize various cardiomyopathy conditions, including dilated cardiomyopathy, hypertrophic cardiomyopathy, myocardial infarction, and abnormal right ventricle. Different activation functions and optimizers were applied to achieve faster convergence. The proposed deep learning framework demonstrated excellent performance, achieving a classification accuracy of 98.9%, effectively distinguishing between multiple categories of cardiomyopathy and related heart diseases.