Update app.py

app.py

@@ -2,21 +2,31 @@ import gradio as gr
 import tensorflow as tf
 import numpy as np
 
-def load_labels(filename):
-    with open(filename, "r") as file:
-        return [line.strip() for line in file.readlines()]
+# Load the trained model once to optimize performance
+model = tf.keras.models.load_model("keras_model.h5")
 
-# Function to load the trained model and predict emotion
-def model_prediction(test_image):
-    model = tf.keras.models.load_model("keras_model.h5")
-    image = tf.keras.preprocessing.image.load_img(test_image, target_size=(48, 48), color_mode="grayscale")
-    input_arr = tf.keras.preprocessing.image.img_to_array(image) / 255.0
-    input_arr = np.expand_dims(input_arr, axis=0)
-    predictions = model.predict(input_arr)
-    return predictions
+# Load labels from the file
+def load_labels(filename):
+    try:
+        with open(filename, "r") as file:
+            return [line.strip() for line in file.readlines()]
+    except FileNotFoundError:
+        return ["happy", "sad", "angry", "fearful", "surprised", "neutral", "fake_expression"]
 
 labels = load_labels("labels.txt")
 
+# Process the input image and get predictions
+def model_prediction(test_image):
+    try:
+        image = tf.keras.preprocessing.image.load_img(test_image, target_size=(48, 48), color_mode="grayscale")
+        input_arr = tf.keras.preprocessing.image.img_to_array(image) / 255.0
+        input_arr = np.expand_dims(input_arr, axis=0)
+        predictions = model.predict(input_arr)
+        return predictions
+    except Exception as e:
+        return str(e)
+
+# Generate color-coded danger levels
 def get_color(value):
     if value >= 75:
         return "label_red"
@@ -25,31 +35,40 @@ def get_color(value):
     else:
         return "label_green"
 
+# Create a styled label box
 def create_colored_box(value):
     color_class = get_color(value)
     return gr.Label(value=f"{value:.2f}%", elem_id=color_class)
 
+# Predict emotion and danger level
 def predict_emotion(test_image):
-    predictions = model_prediction(test_image)
-    emotion_index = np.argmax(predictions)
-    emotion_probability = predictions[0][emotion_index] * 100
-    emotion_name = labels[emotion_index]
-
-    # Predict level of danger based on emotion
-    danger_level = 0
-    if emotion_name == "sad":
-        danger_level = min(100, emotion_probability * 1.2)
-    elif emotion_name == "fearful":
-        danger_level = min(100, emotion_probability * 1.5)
-    elif emotion_name == "fake_expression":
-        danger_level = 70  # Example fixed percentage for fake expression
+    try:
+        predictions = model_prediction(test_image)
+        if isinstance(predictions, str):  # Handle error
+            return ("Error", predictions, "N/A")
 
-    return (
-        emotion_name, 
-        create_colored_box(emotion_probability), 
-        create_colored_box(danger_level)
-    )
+        emotion_index = np.argmax(predictions)
+        emotion_probability = predictions[0][emotion_index] * 100
+        emotion_name = labels[emotion_index]
+
+        # Calculate danger level
+        danger_level = 0
+        if emotion_name == "sad":
+            danger_level = min(100, emotion_probability * 1.2)
+        elif emotion_name == "fearful":
+            danger_level = min(100, emotion_probability * 1.5)
+        elif emotion_name == "fake_expression":
+            danger_level = 70  # Example fixed percentage for fake expression
 
+        return (
+            emotion_name, 
+            create_colored_box(emotion_probability), 
+            create_colored_box(danger_level)
+        )
+    except Exception as e:
+        return ("Error", str(e), "N/A")
+
+# Home tab content
 def home():
     return (
         "# Welcome to Emotion Analysis for Women Safety! 🌟\n\n"
@@ -65,13 +84,15 @@ def home():
         "3. Take necessary actions based on insights."
     )
 
+# Gradio Interface
 with gr.Blocks(css=""" 
 .label_green { background-color: green; color: white; }
 .label_yellow { background-color: yellow; color: black; }
 .label_red { background-color: red; color: white; }
 """) as demo:
     gr.Markdown("# Emotion Analysis for Women Safety")
-    gr.Image("logo.webp")
+    gr.Image("logo.webp", elem_id="app_logo", show_label=False, label="App Logo")
+
     with gr.Tabs():
         with gr.TabItem("Home"):
             gr.Markdown(home())