Update app.py

app.py

@@ -5,7 +5,7 @@ import numpy as np
 from tensorflow.keras.preprocessing import image
 
 
-def predict_image(input_image):
+def predict_image(input_image, threshold=0.5):
     # Load and preprocess the input image
     img = image.load_img(input_image, target_size=(224, 224))
     img = image.img_to_array(img)
@@ -17,12 +17,16 @@ def predict_image(input_image):
     loaded_model = load_model('tumor_model.h5')
     predictions = loaded_model.predict(img)
 
-    # Assuming it's a binary classification model, you can interpret the prediction
-    class_names = ['yes', 'no']
-    class_index = int(round(predictions[0][0]))
-    class_name = class_names[class_index]
+    # Assuming it's a binary classification model
+    predicted_probability = predictions[0][0]
+
+    # Determine the class based on the threshold
+    if predicted_probability > threshold:
+        class_name = 'tumor'
+    else:
+        class_name = 'no tumor'
 
     return f'Predicted Class: {class_name}'
 
-iface = gr.Interface(fn=predict_image, inputs="image", outputs="text")
+iface = gr.Interface(fn=predict_image, inputs="image", outputs="text", live=True)
 iface.launch(share=True)