Update app.py

app.py

@@ -3,34 +3,51 @@ import tensorflow as tf
 import numpy as np
 import gradio as gr
 import io
+import json
 
 # Load the model
 model_path = 'final_teath_classifier.h5'
 model = tf.keras.models.load_model(model_path)
 
+# Define preprocessing function
+
+
 # Define prediction function
 def predict_image(image):
-    # Load and preprocess the image
+    # Save the image to a file-like object
+    image_bytes = io.BytesIO()
+    image.save(image_bytes, format="JPEG")
+
+    # Load the image from the file-like object
+    image = tf.keras.preprocessing.image.load_img(image_bytes, target_size=(256, 256))
     image = np.array(image)/255
     image = np.expand_dims(image, axis=0)
 
-    # Make predictions
-    predictions = model.predict(image)
+    # Make a prediction
+    prediction = model.predict(image)
 
-    # Get the predicted class and probability
-    predicted_class_index = np.argmax(predictions)
-    predicted_label = "Clean" if predicted_class_index == 0 else "Carries"
-    predicted_probability = np.max(tf.nn.softmax(predictions))
+    # Get the probability of being 'Clean' or 'Carries'
+    probabilities = tf.nn.softmax(prediction, axis=-1)
+    predicted_class_index = np.argmax(probabilities)
+    if predicted_class_index == 0:
+        predicted_label = "Clean"
+        #predicted_probability = probabilities[0][0] * 100  # Convert to percentage
+    else:
+        predicted_label = "Carries"
+        #predicted_probability = probabilities[0][1] * 100  # Convert to percentage
 
     # Return the prediction result as a dictionary
-    return {"Predicted Label": predicted_label, "Probability": f"{predicted_probability * 100:.2f}%"}
+    return {"Predicted Label": predicted_label}
+
 
 # Create the interface
 input_interface = gr.Image(type="pil")
+output_interface = "json"
+
 iface = gr.Interface(
     fn=predict_image,
     inputs=input_interface,
-    outputs="json")
+    outputs=output_interface)
 
 # Launch the interface
-iface.launch(share=True)
+iface.launch(share=True)