In recent days, skin cancer is seen as one of the most Hazardous forms of the Cancers found in Humans. Skin cancer is found in various types such as Melanoma, Basal and Squamous cell Carcinoma among which Melanoma is the most unpredictable. Early detection of Melanoma can potentially improve survival rate. In this project, we will study the performance of various Convolution Neural Network models for diagnosing melanoma, the deadliest form of skin cancer. Which is helpful for identification of melanoma disease at an early stage.