Update app.py

app.py

@@ -1,14 +1,13 @@
 import subprocess
-import os
 
-# Define the list of libraries to install with specific versions
+# Define the list of libraries to install
 libraries = [
-    'gradio==2.3.0',                # You can update to a more recent version if needed
-    'tensorflow==2.12.0',           # Use a more recent version available on your platform
-    'numpy==1.23.5',                # Compatible with TensorFlow 2.12.0 and newer versions of matplotlib
-    'Pillow==8.4.0',
-    'opencv-python-headless==4.5.5.62',  # This installs OpenCV without GUI support
-    'pandas==1.4.2',                # Ensure compatibility with numpy
+    'gradio',
+    'tensorflow',
+    'numpy',
+    'Pillow',
+    'opencv-python-headless',
+    'Flask'  # Add Flask here
 ]
 
 # Install each library using pip
@@ -24,17 +23,8 @@ import numpy as np
 from PIL import Image
 import io
 
-# Load the pre-trained TensorFlow model from the specified path
-model_path = "imageclassifier.h5"
-
-# Check if the model file exists
-if not os.path.exists(model_path):
-    raise FileNotFoundError(f"Model file not found at path: {model_path}")
-
-try:
-    model = tf.keras.models.load_model(model_path, custom_objects=None, compile=True)
-except Exception as e:
-    raise IOError(f"Error loading model from {model_path}: {e}")
+# Load the pre-trained TensorFlow model
+model = tf.keras.models.load_model("imageclassifier.h5")
 
 # Define the function to predict the teeth health
 def predict_teeth_health(image):
@@ -53,18 +43,19 @@ def predict_teeth_health(image):
     # Get the probability of being 'Good'
     probability_good = prediction[0][0]  # Assuming it's a binary classification
 
-    # Return the predicted class name
-    if probability_good > 0.5:
-        return f"Predicted: Your Teeth are Good And You Don't Need To Visit Doctor"
-    else:
-        return f"Predicted: Your Teeth are Bad And You Need To Visit Doctor"
+    # Define the prediction result
+    result = {
+        "prediction": "Your Teeth are Good & You Don't Need To Visit Doctor" if probability_good > 0.5 else "Your Teeth are Bad & You Need To Visit Doctor"
+    }
+
+    return result
 
 # Define the Gradio interface
 iface = gr.Interface(
     fn=predict_teeth_health,
-    inputs=gr.inputs.Image(type="pil"),
-    outputs="text",
-    title="<h1 style='color: lightgreen; text-align: center;'>Dentella</h1>",
+    inputs=gr.Image(type="pil"),
+    outputs="json",
+    title="<h1 style='color: lightgreen; text-align: center;'>Dentella</h1><p style='text-align: center; color: skyblue; font-size: 30px;'>Please Enter Your Teeth Here...</p>",
 )
 
 # Deploy the Gradio interface using Gradio's hosting service