Update app.py

app.py

@@ -4,22 +4,20 @@ import tensorflow as tf
 from tensorflow.keras.models import load_model
 from PIL import Image
 
-# Load your model
+# Load the model
 model = load_model("model.h5")
 
-# Define class names (change these to match your training labels)
+# Your class labels (update as per your model)
 class_names = ['Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral']
 
 # Prediction function
 def predict_expression(image):
     try:
-        # Convert to grayscale if model expects 1 channel
-        image = image.convert("L")  # grayscale
-        image = image.resize((48, 48))  # match training size
+        image = image.convert("RGB")  # Ensure 3 channels
+        image = image.resize((224, 224))  # Resize to model's expected input
         img_array = np.array(image).astype("float32") / 255.0
-        img_array = img_array.reshape(1, 48, 48, 1)  # (batch, height, width, channels)
+        img_array = img_array.reshape(1, 224, 224, 3)
 
-        # Predict
         prediction = model.predict(img_array)
         class_idx = int(np.argmax(prediction))
         confidence = float(np.max(prediction))
@@ -29,7 +27,7 @@ def predict_expression(image):
     except Exception as e:
         return f"⚠️ Error: {str(e)}"
 
-# Gradio Interface
+# Gradio interface
 iface = gr.Interface(
     fn=predict_expression,
     inputs=gr.Image(type="pil"),