How to use sarasij907/emotion-detection-efficientnet with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://sarasij907/emotion-detection-efficientnet")
ImageNet-pretrained EfficientNetB0 fine-tuned with 5-fold stratified validation. Classes: angry, disgust, fear, happy, neutral, sad, surprise. Mean validation accuracy: 0.5596. Input: RGB image resized to 224x224.
