Update app.py

app.py

@@ -1,31 +1,23 @@
 import gradio as gr
 import tensorflow as tf
-import numpy as np
-import time
 
-# Load the model once at the start
-model = tf.keras.models.load_model("model/keras_model.h5")
+import numpy as np
 
-# Function to load labels
 def load_labels(filename):
     with open(filename, "r") as file:
         return [line.strip() for line in file.readlines()]
 
-labels = load_labels("labels.txt")
-
-# Function to preprocess image and predict emotion
+# Function to load the trained model and predict emotion
 def model_prediction(test_image):
+    model = tf.keras.models.load_model("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)
-
-    # Measure prediction time
-    start_time = time.time()
     predictions = model.predict(input_arr)
-    print("Prediction time:", time.time() - start_time)
     return predictions
 
-# Get color based on value
+labels = load_labels("labels.txt")
+
 def get_color(value):
     if value >= 75:
         return "label_red"
@@ -34,26 +26,24 @@ def get_color(value):
     else:
         return "label_green"
 
-# Create colored box for percentage
 def create_colored_box(value):
     color_class = get_color(value)
     return gr.Label(value=f"{value:.2f}%", elem_id=color_class)
 
-# Main prediction function
 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]
 
-    # Calculate danger level based on emotion
+    # 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  # Fixed value for fake expression
+        danger_level = 70  # Example fixed percentage for fake expression
 
     return (
         emotion_name, 
@@ -61,7 +51,6 @@ def predict_emotion(test_image):
         create_colored_box(danger_level)
     )
 
-# Home page content
 def home():
     return (
         "# Welcome to Emotion Analysis for Women Safety! 🌟\n\n"
@@ -77,20 +66,19 @@ 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")  # Replace with your logo or remove if not available
+    gr.Image("logo.webp")
     with gr.Tabs():
         with gr.TabItem("Home"):
             gr.Markdown(home())
         with gr.TabItem("Emotion Analysis"):
             gr.Markdown("## Upload a facial image for emotion analysis:")
-            test_image = gr.Image(type="filepath", label="Upload Image", tool="editor")
+            test_image = gr.Image(type="filepath", label="Upload Image")
 
             with gr.Row():
                 predict_btn = gr.Button("Analyze Emotion")
@@ -98,11 +86,10 @@ with gr.Blocks(css="""
             probability_label = gr.Label(label="Emotion Probability")
             danger_label = gr.Label(label="Danger Level (%)")
 
-            predict_btn.click(
-                predict_emotion, 
-                inputs=test_image, 
-                outputs=[emotion_label, probability_label, danger_label]
-            )
+            predict_btn.click(predict_emotion, inputs=test_image, outputs=[
+                emotion_label, 
+                probability_label, 
+                danger_label
+            ])
 
-# Launch the app
-demo.launch()
+demo.launch()