Skin is an outer covering of body that acts as protection layer from the UV rays of sun. Nowadays, skin disease cases are increasing, so there is a need of a system that can detect skin disease at an early stage. Deep learning is the most efficient, supervised, time- and cost-effective method that has attained outstanding performance in the medical field. These algorithms are fast, and has shown their success and adaptability in different sectors. In this paper, a pre-trained Mobilenet architecture is modified by removing the last five layers and adding one average pooling layer, one dropout layer and one dense layer. The modified Mobilenet architecture is simulated on HAM10000 skin disease dermoscopy dataset. Different transformation techniques have been applied for data augmentation to solve the problem of data imbalance. The model has attained an accuracy of 90%, followed by precision of 86.14%.