Monkey Species Classifier — with Grad-CAM Interpretability
A VGG16 transfer-learning CNN classifies 10 monkey species from a photo. The right-hand panel shows the Grad-CAM heatmap — the regions of the image the model used to make its decision.
This is what interpretability looks like in practice: instead of trusting a black-box prediction, you can verify the model is looking at the monkey's features and not at random background details.
Heads-up on limitations: the model only knows the 10 species listed below (it's not a general "what monkey is this" classifier). It also works best with clear photos where the monkey is the subject — extreme angles, heavy occlusion, or non-monkey primates will confuse it. Pick a sample below to see typical behavior, then upload your own.
Pick a sample below or upload a monkey photo — prediction runs automatically.