The snake species can be manually identified based on some features such as head shape, body shape, body texture, skin color, and eye shape, which are not common for non-expert people. An automatic classification of a snake species based on its image is already developed using a traditional machine learning technique, but the parameters should be manually tuned. Therefore, in this paper a convolutional neural network (CNN) is used to develop such classification. Three CNN architectures are evaluated using a dataset of 415 snake images from five common hazardous venomous snake species in Indonesia. Five-fold cross-validating shows that CNN is capable of classifying the snake images with a high accuracy of 82 percent.