One of the most dangerous types of skin cancer is melanoma, which can be fatal if not caught early. Therefore, melanoma detection requires a precise diagnosis. A dermatologist typically uses a microscope to examine and then report on a biopsy to make a diagnosis, but this process is difficult and requires experience. Therefore, it is necessary to make the diagnosing procedure easier while yet producing a precise diagnosis. Artificial intelligence algorithms can help the dermatologist make a diagnosis for this reason. In this study, we took into account the deep learning-based melanoma detection using cutaneous image processin/**/+-zg. To do this, we examined a variety of deep learning (DL) architectures and assessed the corresponding deep learning models on graphics processing units. Using common machine learning measures like accuracy, precision, recall, and F1-score, the experimental findings demonstrated that the proposed model can achieve the maximum performance accuracy on both the training and test sets. Keywords: deep learning; dermatology; skin cancer; melanoma images.