part 2

app.py

@@ -1,8 +1,7 @@
-import gradio as gr
 import tensorflow as tf
 import numpy as np
-from PIL import Image
 import cv2
+import gradio as gr
 
 # Load the model
 model = tf.keras.models.load_model('eyeStateModel.h5')
@@ -12,7 +11,7 @@ def preprocess_image(image):
     if len(image.shape) == 2:
         image = cv2.cvtColor(image, cv2.COLOR_GRAY2RGB)
     
-    # Resize image to match model's expected sizing
+    # Resize image to 224x224 (matching the model's expected input)
     image = cv2.resize(image, (224, 224))
     
     # Normalize pixel values
@@ -34,23 +33,29 @@ def predict_eye_state(image):
     confidence = float(prediction[0][predicted_class])
     
     # Map prediction to class name
-    class_names = ['Closed Eyes', 'Open Eyes']
+    class_names = ['Eyes Closed', 'Eyes Open']
     result = class_names[predicted_class]
     
-    # Return result and confidence
-    return {result: confidence, class_names[1-predicted_class]: 1-confidence}
+    # Create confidence dict
+    confidences = {
+        class_names[0]: float(prediction[0][0]),
+        class_names[1]: float(prediction[0][1])
+    }
+    
+    return confidences
 
 # Create Gradio interface
-iface = gr.Interface(
+demo = gr.Interface(
     fn=predict_eye_state,
-    inputs=gr.Image(type="numpy"),
+    inputs=gr.Image(),
     outputs=gr.Label(num_top_classes=2),
     examples=[
-        ["example1.jpg"],
-        ["example2.jpg"]
+        ["sample1.jpg"],
+        ["sample2.jpg"]
     ],
     title="Eye State Detection",
-    description="Upload an image to detect if the eyes are open or closed.",
+    description="Upload an image of eyes to detect if they are open or closed.",
 )
 
-iface.launch()
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -1,5 +1,4 @@
 tensorflow==2.13.0
-gradio==4.1.1
-Pillow==10.0.0
+Pillow==9.3.0
 numpy==1.23.5
-opencv-python-headless==4.8.1.78
+opencv-python-headless==4.8.0.74