Update app.py

app.py

@@ -1,35 +1,55 @@
 import gradio as gr
-from fastai.vision.all import *
+from fastai.vision.all import load_learner, PILImage
+from PIL import Image
+import torch
 
-# Load your trained model (replace with your model path)
-model_path = "efficientnet_emotion_model.pkl"
+# Define the class mapping for the RAF-DB dataset
+class_mapping = {
+    "1": "Surprise",
+    "2": "Fear",
+    "3": "Disgust",
+    "4": "Happiness",
+    "5": "Sadness",
+    "6": "Anger",
+    "7": "Contempt"
+}
+
+# Define the function to map folder names to labels
+def get_raf_label(file_path):
+    # Use the class mapping to get the label
+    return class_mapping[str(file_path.parent.name)]
+
+# Load the model
+model_path = "Emotion_model_vggface2.pkl"  # Replace with your actual model path
 model = load_learner(model_path)
 
-# Emotion prediction function with percentage
-def predict_emotion(image):
-    # Perform prediction using your trained model
-    pred_class, pred_idx, outputs = model.predict(image)
-    
-    # Get the probability (confidence) of the prediction
+# Define the emotion classes
+emotion_classes = list(class_mapping.values())  # Get emotion classes from the class mapping
+
+# Gradio interface
+st.title("Emotion Recognition Classifier")
+
+# Upload an image
+file = st.file_uploader("Upload an image of a face", type=["jpeg", "jpg", "png"])
+
+if file is None:
+    st.write("Please upload an image to detect the emotion.")
+else:
+    # Display the uploaded image
+    image = Image.open(file)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    # Convert the image to a format that the model can accept
+    img = PILImage.create(file)
+
+    # Predict the emotion
+    st.write("Classifying the emotion...")
+    pred_class, pred_idx, outputs = model.predict(img)
+
+    # Get the predicted label and confidence
+    predicted_emotion = emotion_classes[pred_idx]
     confidence = outputs[pred_idx] * 100  # Convert to percentage
-    
-    return f"Predicted Emotion: {pred_class}", f"Confidence: {confidence:.2f}%"
-
-# Create the Gradio interface
-with gr.Blocks(theme='gstaff/xkcd') as demo:
-    gr.Markdown("# Emotion Recognition Classifier")
-    
-    with gr.Row():
-        with gr.Column():
-            # Image input widget
-            img_input = gr.Image(type="pil", label="Upload an image")
-            
-            # Text output widgets for emotion prediction and confidence percentage
-            label_output = gr.Textbox(label="Predicted Emotion")
-            confidence_output = gr.Textbox(label="Confidence Percentage")
-            
-            # Button to trigger emotion classification
-            img_input.upload(predict_emotion, img_input, [label_output, confidence_output])
-    
-    # Run the app
-    demo.launch(share=True)
+
+    # Show results
+    st.write(f"**Predicted Emotion:** {predicted_emotion}")
+    st.write(f"**Confidence:** {confidence:.2f}%")