A deep learning project for 7-class Facial Expression Recognition with post-hoc explainability using LIME and SHAP. Two CNN architectures — ResNet-50 and EfficientNet-B0 — are trained and evaluated on FER2013 and RAF-DB, with pixel-level and region-level explanations generated for every prediction.
numpy cuda cnn torch pandas seaborn matplotlib transfer-learning lime fer2013 resnet50 shap efficientnet rafdb cosineannealingwarmrestarts freezing-layer
-
Updated
Jul 1, 2026 - HTML