Tensorflow, an open source library for Machine Learning developed by Google, comes with a demo program that labels images. The output of the program contains the labels (or class names) and their scores. The score represents the probability of the image to belong to a certain class.
green mamba (score = 0.43074)
vine snake (score = 0.18073)
shoji (score = 0.02248)
shower curtain (score = 0.01834)
African chameleon, Chamaeleo chamaeleon (score = 0.01708)
The program uses a model trained with the ImageNet dataset. So here is what the model used to create an internal representation of what a green mamba is. Add a touch of shower curtain and what do we get: comparative vandalism?