FER-2013 Emotion Classifier (Augmented)
A Keras CNN trained on FER-2013 with Albumentations augmentation and class-weighting.
Files
- `emotion_model_augmented.h5`: best checkpoint weights + architecture
- `emotion_model_saved/`: (optional) TensorFlow SavedModel export
Usage
```python
from huggingface_hub import from_pretrained_keras
model = from_pretrained_keras("AS1888/fer2013-emotion-classifier")
Prepare a single PIL image:
img = img.convert("L").resize((96,96))
x = np.array(img)/255.0
x = x[np.newaxis,...,np.newaxis]
preds = model.predict(x)
```
